© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 111777
    Prev
    Next
    INDEX
    Explanations

    the

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     نقل
    -0.08
     Ca
    -0.07
     VECTOR
    -0.07
     walked
    -0.06
     phù
    -0.06
     Aur
    -0.06
    -package
    -0.06
     chaining
    -0.06
     komt
    -0.06
    _loc
    -0.06
    POSITIVE LOGITS
    SuppressLint
    0.07
    .strategy
    0.07
    ozici
    0.06
    AnimationFrame
    0.06
     득
    0.06
    宋体
    0.06
    ísk
    0.06
     созд
    0.06
    /start
    0.06
     RTWF
    0.06
    Activations Density 0.058%

    No Known Activations