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. 11-RESID-POST-AA
    6. 93063
    Prev
    Next
    INDEX
    Explanations

    cell biology

    np_max-act · gemini-2.0-flash

    The neuron activates on floating‐point numeric tokens (decimal measurement values).

    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
     Withdraw
    -0.07
    existent
    -0.07
     While
    -0.07
    _CONST
    -0.07
    701
    -0.07
    api
    -0.07
    .offset
    -0.07
    oh
    -0.07
     dir
    -0.06
     swamp
    -0.06
    POSITIVE LOGITS
     l�
    0.06
    ?<
    0.06
     псих
    0.06
    ραση
    0.06
    (dAtA
    0.06
    ¬
    0.06
    _________________↵↵
    0.05
    Enterprise
    0.05
    男性
    0.05
    getElement
    0.05
    Activations Density 0.019%

    No Known Activations