© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 49624
    Prev
    Next
    INDEX
    Explanations

    Reporting information

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comer
    -0.07
    数字
    -0.06
    errMsg
    -0.06
    раниц
    -0.06
    testCase
    -0.06
     gebru
    -0.06
    ."&
    -0.06
    냐
    -0.06
     ци
    -0.05
    quivos
    -0.05
    POSITIVE LOGITS
    _SPECIAL
    0.07
     french
    0.07
    _DET
    0.06
    .ex
    0.06
    _OPT
    0.06
    ’nda
    0.06
     Fold
    0.06
    cret
    0.06
    nore
    0.06
    _AHB
    0.06
    Activations Density 0.425%

    No Known Activations