© 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. 75364
    Prev
    Next
    INDEX
    Explanations

    -able

    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
     reinforces
    -0.07
     reinst
    -0.06
    407
    -0.06
    _id
    -0.06
    _Part
    -0.06
     verst
    -0.06
     pět
    -0.06
    venues
    -0.06
     crus
    -0.06
    归
    -0.06
    POSITIVE LOGITS
    able
    0.15
    ABLE
    0.13
    ables
    0.11
    ible
    0.11
    IBLE
    0.09
    earable
    0.08
    ibles
    0.08
    abe
    0.08
    abwe
    0.08
    datatable
    0.08
    Activations Density 0.205%

    No Known Activations