Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 9934
    Prev
    Next
    INDEX
    Explanations

    Code/Technical documentation

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LEVEL
    -0.07
    Videos
    -0.07
    _equ
    -0.07
    Producto
    -0.07
    assin
    -0.06
     pinch
    -0.06
     xã
    -0.06
    atter
    -0.06
    ());↵↵↵
    -0.06
    )))↵↵↵
    -0.06
    POSITIVE LOGITS
    roulette
    0.07
     //----------------
    0.07
     effective
    0.07
     기본
    0.07
     Filter
    0.06
     همه
    0.06
    지노
    0.06
    .selenium
    0.06
     파일
    0.06
    .Touch
    0.06
    Activations Density 0.091%

    No Known Activations