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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RESID-POST-AA
    6. 130681
    Prev
    Next
    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literal tokens, especially floating‐point constants.

    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
    liğine
    -0.06
    Ping
    -0.06
    _PARSE
    -0.06
    :NSMakeRange
    -0.06
    aversal
    -0.06
     vhodné
    -0.06
    utches
    -0.06
    �
    -0.06
     implementation
    -0.06
    -end
    -0.06
    POSITIVE LOGITS
     고객
    0.08
     تقو
    0.07
    .total
    0.07
    }}
    0.07
     thu
    0.06
     діяль
    0.06
    */↵
    0.06
    廊
    0.06
     thous
    0.06
    ��
    0.06
    Activations Density 0.009%

    No Known Activations