Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 27-RESID-POST-AA
    6. 73442
    Prev
    Next
    INDEX
    Explanations

    vert

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     پای
    -0.07
     조선
    -0.07
     पड
    -0.07
     congreg
    -0.07
     gradu
    -0.07
     sö
    -0.06
    icago
    -0.06
    iscing
    -0.06
    _fid
    -0.06
    이고
    -0.06
    POSITIVE LOGITS
    -active
    0.07
    äl
    0.07
     credible
    0.06
    aların
    0.06
     initialState
    0.06
    _feature
    0.06
    魚
    0.06
     rootReducer
    0.06
    anni
    0.06
    ilmektedir
    0.06
    Activations Density 0.002%

    No Known Activations