Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 103998
    Prev
    Next
    INDEX
    Explanations

    Code and system fabric

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Samsung
    -0.07
    //↵
    -0.07
     daughters
    -0.07
    prises
    -0.06
     Ultr
    -0.06
     خو
    -0.06
     зуб
    -0.06
    <QString
    -0.06
    Videos
    -0.06
    tır
    -0.06
    POSITIVE LOGITS
     şeklinde
    0.07
    (pair
    0.06
    /he
    0.06
     bicy
    0.06
    rea
    0.06
    .''
    0.06
    classed
    0.06
    =*/
    0.06
    ivating
    0.06
    ."'
    0.06
    Activations Density 0.005%

    No Known Activations