© 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. 3-RESID-POST-AA
    11. 121604
    Prev
    Next
    INDEX
    Explanations

    and

    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
    .pix
    -0.08
    accuracy
    -0.07
    _POINT
    -0.07
    _datas
    -0.07
    $n
    -0.06
     glUniform
    -0.06
     Example
    -0.06
    -files
    -0.06
     koşul
    -0.06
    ="--
    -0.06
    POSITIVE LOGITS
     JA
    0.07
    (",
    0.06
    -and
    0.06
    within
    0.06
    *******
↵
    0.06
    but
    0.06
     wherever
    0.06
     ;
↵
    0.06
    �
    0.06
    .A
    0.06
    Activations Density 0.213%

    No Known Activations