© 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. 27-RESID-POST-AA
    11. 102724
    Prev
    Next
    INDEX
    Explanations

    Audio and sound cards

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     practiced
    -0.07
    etheus
    -0.07
    NewProp
    -0.07
    شركة
    -0.06
    پ
    -0.06
    Versions
    -0.06
     synthesized
    -0.06
    うち
    -0.06
     goo
    -0.06
     tongue
    -0.06
    POSITIVE LOGITS
    ouv
    0.07
    izzly
    0.06
     gameTime
    0.06
     เคร
    0.06
     Aspect
    0.06
    _dirty
    0.06
    .Lock
    0.06
    )NSString
    0.06
     gef
    0.06
     integerValue
    0.06
    Activations Density 0.015%

    No Known Activations