© 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. 110095
    Prev
    Next
    INDEX
    Explanations

    serving as

    np_max-act · gemini-2.0-flash

    The neuron fires on the word “as” when it introduces a role or function (e.g. “serving as…,” “operating as…”).

    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
    方面
    -0.07
     अश
    -0.07
     Birliği
    -0.06
     lament
    -0.06
    _book
    -0.06
    ��
    -0.06
    /source
    -0.06
     그녀는
    -0.06
     usher
    -0.06
     Strom
    -0.06
    POSITIVE LOGITS
    extView
    0.06
     rigged
    0.06
                
    0.06
    -inv
    0.06
    htub
    0.06
    adia
    0.06
     suffice
    0.06
    قت
    0.06
     přem
    0.06
    LABEL
    0.06
    Activations Density 0.031%

    No Known Activations