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. 83603
    Prev
    Next
    INDEX
    Explanations

    punctuation/separators

    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
     rotated
    -0.06
    cribing
    -0.06
    cen
    -0.06
     Rates
    -0.06
    vol
    -0.06
     chuyện
    -0.06
    getX
    -0.06
     adı
    -0.06
     besoin
    -0.06
    cities
    -0.06
    POSITIVE LOGITS
    (payload
    0.07
    IF
    0.07
    });
    0.07
     řešení
    0.06
    urse
    0.06
     instruct
    0.06
    AGE
    0.06
    _DROP
    0.06
     вищ
    0.06
    rbrace
    0.06
    Activations Density 0.001%

    No Known Activations