© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 90427
    Prev
    Next
    INDEX
    Explanations

    nearly/almost

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    フォ
    -0.07
    STRU
    -0.07
    女性
    -0.07
    败
    -0.07
     başk
    -0.07
    exo
    -0.06
    '|
    -0.06
     STUD
    -0.06
    |l
    -0.06
    duce
    -0.06
    POSITIVE LOGITS
     nearly
    0.08
    (BASE
    0.07
     почти
    0.07
    .sales
    0.07
     정말
    0.07
     Almost
    0.07
    illy
    0.07
     тих
    0.07
    ň
    0.07
    _AMOUNT
    0.06
    Activations Density 0.009%

    No Known Activations