© 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. 75830
    Prev
    Next
    INDEX
    Explanations

    Stop words

    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
    utorials
    -0.07
    езультат
    -0.07
    .Main
    -0.07
    EFAULT
    -0.07
     democratic
    -0.07
    станов
    -0.07
    ρέπει
    -0.06
     logical
    -0.06
     대학
    -0.06
    _utilities
    -0.06
    POSITIVE LOGITS
    .cmd
    0.08
    ське
    0.06
    進
    0.06
     thu
    0.06
     pł
    0.06
     viewBox
    0.06
    _season
    0.05
     MaterialApp
    0.05
    .email
    0.05
     Namen
    0.05
    Activations Density 0.148%

    No Known Activations