© 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. 97324
    Prev
    Next
    INDEX
    Explanations

    witness

    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
     Coal
    -0.07
    Explorer
    -0.07
    ao
    -0.07
    42
    -0.07
    .Car
    -0.06
     Gal
    -0.06
    ocomplete
    -0.06
     Ala
    -0.06
    -olds
    -0.06
     RPG
    -0.06
    POSITIVE LOGITS
     witness
    0.17
     witnessed
    0.17
     Witness
    0.15
     witnessing
    0.14
     witnesses
    0.13
    Witness
    0.12
     eyewitness
    0.11
    itness
    0.11
    ewitness
    0.09
     Witnesses
    0.09
    Activations Density 0.004%

    No Known Activations