© 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. 100031
    Prev
    Next
    INDEX
    Explanations

    fork

    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
    .Field
    -0.07
    .media
    -0.06
     Κου
    -0.06
     conscience
    -0.06
    Lots
    -0.06
     Qin
    -0.06
    atic
    -0.06
     lots
    -0.06
     ecology
    -0.06
    @Entity
    -0.06
    POSITIVE LOGITS
    Interested
    0.06
    rieb
    0.06
    ників
    0.06
     ArgumentException
    0.06
    observation
    0.06
     grateful
    0.06
     arrived
    0.06
     hm
    0.06
     conditioned
    0.06
    icester
    0.06
    Activations Density 0.012%

    No Known Activations