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. 29193
    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_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
    ına
    -0.07
     small
    -0.07
     department
    -0.07
    chein
    -0.07
    ाग
    -0.06
    )?↵↵
    -0.06
    อนด
    -0.06
     багатьох
    -0.06
    (toolbar
    -0.06
    .histogram
    -0.06
    POSITIVE LOGITS
    RIC
    0.06
    FORCE
    0.06
    сы
    0.06
    .styleable
    0.06
    theast
    0.06
    ngthen
    0.06
     silent
    0.06
     Milit
    0.06
     Vanity
    0.06
    lerinin
    0.06
    Activations Density 0.075%

    No Known Activations