© 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
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 40672
    Prev
    Next
    INDEX
    Explanations

    of

    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
    ับ
    -0.07
     highlighting
    -0.07
    มาร
    -0.07
    شته
    -0.07
     duyệt
    -0.07
    YTE
    -0.07
     Priest
    -0.07
     prestige
    -0.07
     achievable
    -0.06
     Zodiac
    -0.06
    POSITIVE LOGITS
     ड
    0.06
     vài
    0.06
    PGA
    0.06
    สด
    0.06
    "?↵↵
    0.06
    .Remote
    0.05
     INA
    0.05
    cff
    0.05
     jmen
    0.05
     flirt
    0.05
    Activations Density 0.009%

    No Known Activations