© 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. 90642
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    np_max-act · gemini-2.0-flash

    The neuron is detecting personal and possessive pronouns (e.g. “their,” “his,” “him”).

    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
    请求
    -0.07
    })"↵
    -0.07
     usuario
    -0.06
     heavy
    -0.06
    ZIP
    -0.06
     share
    -0.06
     coffee
    -0.06
    minimum
    -0.06
     인간
    -0.06
     today
    -0.06
    POSITIVE LOGITS
    (Packet
    0.07
     Detect
    0.07
     -,
    0.06
     UNC
    0.06
    incl
    0.06
     pData
    0.06
     Increment
    0.06
    841
    0.06
    .MiddleCenter
    0.06
     ولم
    0.06
    Activations Density 0.138%

    No Known Activations