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. 19-RESID-POST-AA
    6. 9348
    Prev
    Next
    INDEX
    Explanations

    Herbert

    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
    ScrollIndicator
    -0.07
     Superior
    -0.07
    ��
    -0.06
    masters
    -0.06
    론
    -0.06
    ılıp
    -0.06
    _terminal
    -0.06
     cel
    -0.06
    _book
    -0.06
     ServiceProvider
    -0.06
    POSITIVE LOGITS
    Slim
    0.07
     queries
    0.06
     Mets
    0.06
    /pro
    0.06
    'am
    0.06
     injecting
    0.06
     immoral
    0.06
     sniff
    0.06
     metabolic
    0.06
    -e
    0.06
    Activations Density 0.000%

    No Known Activations