© 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. 15-RESID-POST-AA
    11. 79259
    Prev
    Next
    INDEX
    Explanations

    comma

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Distributed
    -0.08
    ального
    -0.07
    at
    -0.07
    ラ
    -0.06
     early
    -0.06
    ibrate
    -0.06
    Clickable
    -0.06
    doubleValue
    -0.06
     consolation
    -0.06
     awkward
    -0.06
    POSITIVE LOGITS
    ved
    0.06
     Mesa
    0.06
    、​
    0.06
     Ebony
    0.06
     ειδ
    0.06
    �
    0.06
     teamed
    0.06
     Artem
    0.06
    /www
    0.06
     extingu
    0.06
    Activations Density 0.067%

    No Known Activations