© 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. 9125
    Prev
    Next
    INDEX
    Explanations

    means

    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
     RA
    -0.07
    Spy
    -0.07
    PARSE
    -0.07
     får
    -0.07
    _ur
    -0.07
     dummy
    -0.06
    /url
    -0.06
     Directors
    -0.06
    dro
    -0.06
    urrency
    -0.06
    POSITIVE LOGITS
    ří
    0.08
     Gene
    0.06
    ivor
    0.06
     oversee
    0.06
     milestone
    0.06
     квіт
    0.06
     ビ
    0.06
     Josh
    0.05
    /twitter
    0.05
    )^
    0.05
    Activations Density 0.019%

    No Known Activations