© 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. 35933
    Prev
    Next
    INDEX
    Explanations

    sensors

    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
    _PED
    -0.07
     verte
    -0.06
    cv
    -0.06
    éro
    -0.06
     refinery
    -0.06
    advert
    -0.06
     Pep
    -0.06
    _fetch
    -0.06
     počet
    -0.06
    ograd
    -0.06
    POSITIVE LOGITS
    �
    0.06
     lever
    0.06
    .Property
    0.06
    nost
    0.06
     Clamp
    0.06
     Loaded
    0.06
    thinkable
    0.06
    ("("
    0.06
     Plus
    0.06
     scrim
    0.06
    Activations Density 0.010%

    No Known Activations