© 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. 19-RESID-POST-AA
    11. 60127
    Prev
    Next
    INDEX
    Explanations

    Initials/Acronyms/Names

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atabase
    -0.08
    etermined
    -0.07
     room
    -0.07
    etailed
    -0.07
    ocumented
    -0.07
     up
    -0.07
    istribution
    -0.07
     around
    -0.06
    etect
    -0.06
    igital
    -0.06
    POSITIVE LOGITS
    Dem
    0.09
     Dere
    0.09
    dan
    0.09
    dong
    0.09
    DV
    0.09
    DC
    0.08
    dere
    0.08
     DR
    0.08
     Dirk
    0.08
     diss
    0.08
    Activations Density 2.466%

    No Known Activations