© 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. 11-RESID-POST-AA
    6. 109231
    Prev
    Next
    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash

    The neuron is sensitive to floating‐point numeric values (decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Blackburn
    -0.06
    Emergency
    -0.06
     hé
    -0.06
     take
    -0.06
     advantages
    -0.06
     Critical
    -0.06
     proport
    -0.06
    ל
    -0.05
     demande
    -0.05
    /password
    -0.05
    POSITIVE LOGITS
    ullan
    0.08
     واست
    0.08
    制造
    0.07
    \Column
    0.07
    \Validation
    0.07
    航空
    0.07
    quoise
    0.07
     této
    0.07
    }}}
    0.07
    Orientation
    0.06
    Activations Density 0.124%

    No Known Activations