© 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. 99622
    Prev
    Next
    INDEX
    Explanations

    )

    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
    StartTime
    -0.06
     Mart
    -0.06
    ITH
    -0.06
    _P
    -0.06
    OSE
    -0.06
     Tot
    -0.06
    chia
    -0.06
    Nr
    -0.06
    няет
    -0.06
     nosso
    -0.06
    POSITIVE LOGITS
     overlook
    0.08
    -trigger
    0.07
    (Optional
    0.07
     surroundings
    0.07
    xFFFF
    0.07
     enqu
    0.07
    .Basic
    0.07
     presence
    0.07
     shake
    0.07
     كيف
    0.06
    Activations Density 0.007%

    No Known Activations