© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 79429
    Prev
    Next
    INDEX
    Explanations

    code characters

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _txt
    -0.07
     řed
    -0.06
    Mozilla
    -0.06
    بال
    -0.06
     toddler
    -0.06
    XT
    -0.06
    fall
    -0.06
    Criterion
    -0.06
    .dtp
    -0.06
    ullah
    -0.06
    POSITIVE LOGITS
    *i
    0.08
    .includes
    0.07
    -Semit
    0.07
    (att
    0.07
    Buffers
    0.06
     địch
    0.06
     imaginary
    0.06
    *c
    0.06
     alignItems
    0.06
     κο
    0.06
    Activations Density 0.008%

    No Known Activations