© 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. 18094
    Prev
    Next
    INDEX
    Explanations

    physical size

    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
    (Content
    -0.06
    다고
    -0.06
    nout
    -0.06
     분야
    -0.06
     Spart
    -0.06
     مكان
    -0.06
    .builders
    -0.06
    AUTHORIZED
    -0.06
    _draft
    -0.06
    Repositories
    -0.06
    POSITIVE LOGITS
     recession
    0.08
     length
    0.08
     सच
    0.07
     shouldn
    0.07
    	mysqli
    0.07
    	expected
    0.07
     reach
    0.07
    regs
    0.06
     çift
    0.06
     obtain
    0.06
    Activations Density 0.014%

    No Known Activations