Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 11-RESID-POST-AA
    6. 35702
    Prev
    Next
    INDEX
    Explanations

    Scary

    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
    ropoda
    -0.07
    تیجه
    -0.07
     undermining
    -0.06
     hüküm
    -0.06
    <|end_of_text|>
    -0.06
    (album
    -0.06
    mpp
    -0.06
    eworthy
    -0.06
    useppe
    -0.06
     유지
    -0.06
    POSITIVE LOGITS
     frightening
    0.11
     scare
    0.10
     scared
    0.09
     frightened
    0.09
     scary
    0.08
     scares
    0.08
     scenarios
    0.07
     Sc
    0.07
    长
    0.07
     remotely
    0.07
    Activations Density 0.007%

    No Known Activations