© 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
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 22849
    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
     tiện
    -0.07
    CPF
    -0.06
     statusBar
    -0.06
    Taken
    -0.06
    Pan
    -0.06
    _characters
    -0.06
     несп
    -0.06
    shortcode
    -0.06
    ूच
    -0.06
    šker
    -0.06
    POSITIVE LOGITS
     société
    0.07
    …and
    0.06
     êtes
    0.06
     믿
    0.06
     UL
    0.06
    ılığı
    0.06
    (pop
    0.06
     відповідаль
    0.06
    ]!=
    0.06
     optimizations
    0.06
    Activations Density 0.025%

    No Known Activations