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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 7-RESID-POST-AA
    6. 71937
    Prev
    Next
    INDEX
    Explanations

    limitations

    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
    _Node
    -0.06
    Stmt
    -0.06
    adians
    -0.06
    _quit
    -0.06
    Album
    -0.06
    RSS
    -0.05
    .Se
    -0.05
    .patient
    -0.05
    さんの
    -0.05
     ".",
    -0.05
    POSITIVE LOGITS
    -budget
    0.07
    _generate
    0.07
    phase
    0.06
    (StringUtils
    0.06
     limitations
    0.06
     مي
    0.06
     كم
    0.06
     spielen
    0.06
     grenade
    0.06
    ダ
    0.06
    Activations Density 0.001%

    No Known Activations