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. 15-RESID-POST-AA
    6. 120503
    Prev
    Next
    INDEX
    Explanations

    questions

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     �
    -0.06
     böl
    -0.06
     αρ
    -0.06
     redistrib
    -0.06
     Diğer
    -0.06
    อกาส
    -0.06
     toprak
    -0.06
    бом
    -0.06
     öt
    -0.06
     newfound
    -0.06
    POSITIVE LOGITS
    访问
    0.07
    .ExecuteNonQuery
    0.07
    _ca
    0.07
    _y
    0.06
    .sql
    0.06
     serbest
    0.06
     sł
    0.06
    combe
    0.06
    qualified
    0.06
    quiring
    0.06
    Activations Density 0.010%

    No Known Activations