© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 28093
    Prev
    Next
    INDEX
    Explanations

    protecting

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XD
    -0.07
    _continue
    -0.06
    tica
    -0.06
     itens
    -0.06
     arp
    -0.06
     Coke
    -0.06
     analyse
    -0.06
    BW
    -0.06
    amber
    -0.06
     RESP
    -0.06
    POSITIVE LOGITS
    กำ
    0.07
     св
    0.07
     Subscribe
    0.06
    腹
    0.06
    _Options
    0.06
     alanında
    0.06
     pizza
    0.06
    .']
    0.06
    있
    0.06
     Equipment
    0.06
    Activations Density 0.003%

    No Known Activations