© 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. 9355
    Prev
    Next
    INDEX
    Explanations

    image enhancement

    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
    =null
    -0.07
    зв
    -0.07
    hof
    -0.07
    ibli
    -0.06
     discharge
    -0.06
     corridor
    -0.06
    $q
    -0.06
     sw
    -0.06
    ]byte
    -0.06
    conj
    -0.06
    POSITIVE LOGITS
     memberId
    0.07
     eighteen
    0.07
     وضعیت
    0.06
     personnes
    0.06
     时
    0.06
    �
    0.06
    ôt
    0.06
    уватися
    0.06
     لم
    0.06
     Log
    0.06
    Activations Density 0.088%

    No Known Activations