© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 120791
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    yah
    -0.08
     Adresse
    -0.07
     Krank
    -0.07
    asin
    -0.07
     Hüs
    -0.07
     dispens
    -0.06
     یک
    -0.06
     Logical
    -0.06
    EMALE
    -0.06
     DEN
    -0.06
    POSITIVE LOGITS
    ่าต
    0.08
    }?
    0.07
    ={!
    0.07
    ']=$
    0.07
    .engine
    0.07
    ่า
    0.07
     +%
    0.06
    //$
    0.06
    ;;;;;;;;;;;;;;;;
    0.06
    인트
    0.06
    Activations Density 0.107%

    No Known Activations