© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 128830
    Prev
    Next
    INDEX
    Explanations

    Dates, numbers, email addresses

    np_max-act · gemini-2.0-flash

    market segments related to various industries and sectors.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects industry segment names (e.g. “Metal Mining,” “Steel & Specialty Metals,” “Packaged Food,” “Advertising,” “Hospitals – Acute Care and Specialty,” etc.) as they appear in the market‐segments list.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ObjectType
    -0.08
    .escape
    -0.07
     CGPoint
    -0.07
     Trudeau
    -0.07
    5
    -0.06
     IllegalAccessException
    -0.06
    6
    -0.06
     Carter
    -0.06
     rivers
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    (pm
    0.07
     دوباره
    0.07
          	
    0.07
    ngthen
    0.06
    athom
    0.06
    atient
    0.06
     AMAZ
    0.06
    ♪↵↵
    0.06
    raid
    0.06
    �
    0.06
    Activations Density 1.183%

    No Known Activations