© 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. 19-RESID-POST-AA
    11. 9546
    Prev
    Next
    INDEX
    Explanations

    software license

    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
    ційно
    -0.07
     Holidays
    -0.07
    H
    -0.06
     striving
    -0.06
     prophecy
    -0.06
     Allowed
    -0.06
     (('
    -0.06
     Institutes
    -0.06
    imited
    -0.06
     مرگ
    -0.06
    POSITIVE LOGITS
     [=
    0.07
     acct
    0.06
    /git
    0.06
     cedar
    0.06
     çek
    0.06
    .hidden
    0.06
    .asarray
    0.06
    isto
    0.06
    ณะ
    0.06
    vement
    0.06
    Activations Density 0.039%

    No Known Activations