© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 65809
    Prev
    Next
    INDEX
    Explanations

    request

    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
     shaved
    -0.06
     Abel
    -0.06
     grow
    -0.06
     comes
    -0.06
     οργ
    -0.06
     come
    -0.06
     measurable
    -0.06
     VARIANT
    -0.06
    冠
    -0.06
     enlarged
    -0.06
    POSITIVE LOGITS
     request
    0.11
     requesting
    0.11
     Requests
    0.10
     requested
    0.10
     requests
    0.10
     Request
    0.09
    Requested
    0.08
     requester
    0.08
    _request
    0.08
    facebook
    0.07
    Activations Density 0.036%

    No Known Activations