© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 123185
    Prev
    Next
    INDEX
    Explanations

    idal

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    qu
    -0.06
    Or
    -0.06
    imated
    -0.06
     layoffs
    -0.06
    illisecond
    -0.06
     cites
    -0.06
    (full
    -0.06
    ў
    -0.06
    uced
    -0.06
     Copenhagen
    -0.06
    POSITIVE LOGITS
    idal
    0.11
    _flg
    0.07
    !!
    0.07
    ダー
    0.07
    _gid
    0.06
    兒
    0.06
    XXX
    0.06
     Budd
    0.06
     菲律宾
    0.06
    BAL
    0.06
    Activations Density 0.002%

    No Known Activations