© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 73363
    Prev
    Next
    INDEX
    Explanations

    industry

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    past
    -0.07
    opr
    -0.07
    _raise
    -0.06
     role
    -0.06
    番
    -0.06
    ounc
    -0.06
     noun
    -0.06
     seguir
    -0.06
    xd
    -0.06
     orchestr
    -0.06
    POSITIVE LOGITS
    _Statics
    0.07
    _HIT
    0.07
    ngör
    0.07
     worldview
    0.07
    (UnmanagedType
    0.06
    _Vector
    0.06
     ActivityCompat
    0.06
     *)__
    0.06
    _working
    0.06
     Mitarbeiter
    0.06
    Activations Density 0.030%

    No Known Activations