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. 19065
    Prev
    Next
    INDEX
    Explanations

    ent

    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
     Fa
    -0.07
     Evolution
    -0.06
    stmt
    -0.06
     indica
    -0.06
     depiction
    -0.06
     subsection
    -0.06
     приклад
    -0.06
     Při
    -0.06
    .ws
    -0.06
     başk
    -0.06
    POSITIVE LOGITS
     compartments
    0.06
    .elasticsearch
    0.06
    sea
    0.06
     bitir
    0.06
     pued
    0.06
     العالمية
    0.06
    もっと
    0.06
     gar
    0.06
    _rate
    0.06
    uede
    0.06
    Activations Density 0.001%

    No Known Activations