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. 129342
    Prev
    Next
    INDEX
    Explanations

    ”

    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
    默
    -0.07
     saddened
    -0.06
    “.
    -0.06
    "—
    -0.06
     hroz
    -0.06
     Resolution
    -0.06
     transgender
    -0.06
    �
    -0.06
     anesthesia
    -0.06
    攻击
    -0.06
    POSITIVE LOGITS
     Burton
    0.08
     gastric
    0.07
     perfil
    0.06
    .commit
    0.06
    XT
    0.06
    woods
    0.06
    PPP
    0.06
     Adolescent
    0.06
    .DataSource
    0.06
     Shooting
    0.06
    Activations Density 0.000%

    No Known Activations