© 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. 7-RESID-POST-AA
    6. 129969
    Prev
    Next
    INDEX
    Explanations

    The TOP_ACTIVATING_TEXTS are a variety of contexts that are not centered around one theme.passing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _lambda
    -0.06
    _frequency
    -0.06
    repair
    -0.06
    Im
    -0.06
    Motor
    -0.06
    (url
    -0.06
    lobal
    -0.06
     filmes
    -0.06
    Robin
    -0.06
    Ik
    -0.06
    POSITIVE LOGITS
     '').
    0.07
    fadeOut
    0.07
     FileInputStream
    0.07
    ','".$
    0.07
    "]).
    0.07
     inconsistencies
    0.07
    ,value
    0.07
     ",";↵
    0.07
    .imageView
    0.06
    ']))↵
    0.06
    Activations Density 0.251%

    No Known Activations