© 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. 68910
    Prev
    Next
    INDEX
    Explanations

    concentration, n

    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
     buildup
    -0.07
    \xf
    -0.06
     rozdíl
    -0.06
    щими
    -0.06
    (fun
    -0.06
     coi
    -0.06
     arbitration
    -0.06
     han
    -0.06
     fins
    -0.06
     Replica
    -0.06
    POSITIVE LOGITS
    groups
    0.07
    ":["
    0.07
     importance
    0.07
     withdraw
    0.07
     serviceName
    0.06
     getProduct
    0.06
     sustained
    0.06
     removeObject
    0.06
    NavBar
    0.06
    注册
    0.06
    Activations Density 0.032%

    No Known Activations