© 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. 7-RESID-POST-AA
    11. 112377
    Prev
    Next
    INDEX
    Explanations

    code files

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GA
    -0.07
    _polygon
    -0.07
     svensk
    -0.06
    _EVENTS
    -0.06
    μι
    -0.06
    ducer
    -0.06
    	Int
    -0.06
    ites
    -0.06
    .Up
    -0.06
    人的
    -0.06
    POSITIVE LOGITS
     oficial
    0.07
     plead
    0.06
     '',
    0.06
    }}{{
    0.06
     pigment
    0.06
     LOWER
    0.06
    moduleName
    0.06
     ง
    0.06
     confessed
    0.06
    "#
    0.06
    Activations Density 0.013%

    No Known Activations