© 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. 73819
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    details about technical descriptions and specifications related to products or inventions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on floating‐point numeric tokens (decimal numbers with a period, e.g. “0.38232421875,” “1.8671875,” etc.).

    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
     absent
    -0.06
     Avoid
    -0.06
     الثاني
    -0.06
    after
    -0.06
     refs
    -0.06
     Lenovo
    -0.06
    ord
    -0.06
     MOZ
    -0.06
     tương
    -0.06
    REQUIRED
    -0.06
    POSITIVE LOGITS
    -ms
    0.07
     firmy
    0.06
     фот
    0.06
     симптом
    0.06
    кан
    0.06
    νηση
    0.06
    Pooling
    0.06
    .setRequestHeader
    0.06
    leting
    0.06
    .InputStreamReader
    0.06
    Activations Density 0.299%

    No Known Activations