© 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. 31891
    Prev
    Next
    INDEX
    Explanations

    CDATA

    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
     reef
    -0.07
    isEqualTo
    -0.06
    (segment
    -0.06
    (Local
    -0.06
    ,label
    -0.06
    _embeddings
    -0.06
    <strong
    -0.06
    íně
    -0.06
    兩
    -0.06
    -cross
    -0.06
    POSITIVE LOGITS
    Browse
    0.07
    living
    0.07
    dney
    0.07
    reglo
    0.07
    .kr
    0.06
    .Message
    0.06
    ordinary
    0.06
     Oswald
    0.06
    _chi
    0.06
     getopt
    0.06
    Activations Density 0.001%

    No Known Activations