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. 7-RESID-POST-AA
    6. 36068
    Prev
    Next
    INDEX
    Explanations

    US towns and cities

    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
    _PUSH
    -0.07
    oleans
    -0.07
    elf
    -0.07
    られた
    -0.06
    HttpRequest
    -0.06
     wird
    -0.06
     tiener
    -0.06
    -even
    -0.06
    ric
    -0.06
    xB
    -0.06
    POSITIVE LOGITS
     ((_
    0.07
     Associ
    0.06
    ाइ
    0.06
     Basil
    0.06
    .running
    0.06
     abril
    0.06
    .AutoScaleDimensions
    0.06
     Doesn
    0.06
                                                                  
    0.06
     Albums
    0.06
    Activations Density 0.006%

    No Known Activations