© 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. 11-RESID-POST-AA
    11. 22644
    Prev
    Next
    INDEX
    Explanations

    -

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    證
    -0.07
    load
    -0.06
    limitations
    -0.06
    mares
    -0.06
    locs
    -0.06
     tongues
    -0.06
    inq
    -0.06
    iders
    -0.06
    423
    -0.06
    "That
    -0.06
    POSITIVE LOGITS
     reserved
    0.07
     æ
    0.06
     equival
    0.06
    دود
    0.06
    madı
    0.06
     Manitoba
    0.06
    :%
    0.06
    (delete
    0.06
    =\"%
    0.06
     öldür
    0.06
    Activations Density 0.008%

    No Known Activations