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. 91573
    Prev
    Next
    INDEX
    Explanations

    Negative constraints

    np_max-act · gemini-2.0-flash

    This neuron specifically detects floating‐point numbers (i.e. decimal scores) 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
     Quaternion
    -0.08
    .Orientation
    -0.07
    _panel
    -0.07
    .called
    -0.07
     fleet
    -0.07
    icense
    -0.07
     ListViewItem
    -0.06
     культури
    -0.06
     Seller
    -0.06
     StreamLazy
    -0.06
    POSITIVE LOGITS
     noss
    0.06
     امر
    0.06
     赤
    0.06
    省
    0.06
    agnost
    0.06
     अप
    0.06
     hol
    0.06
    (program
    0.06
     TIMES
    0.06
    mal
    0.05
    Activations Density 0.001%

    No Known Activations