© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30459
    Prev
    Next
    INDEX
    Explanations

    per

    np_max-act · gemini-2.0-flash

    This neuron does not activate on any input patterns and appears to be inactive (a “dead” neuron).

    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
     Obesity
    -0.06
    _execute
    -0.06
    atform
    -0.06
    mah
    -0.06
    uhe
    -0.06
    emu
    -0.06
    clientId
    -0.06
    iento
    -0.06
    ofstream
    -0.05
    Edges
    -0.05
    POSITIVE LOGITS
    ندق
    0.08
     د
    0.07
     pra
    0.06
     savvy
    0.06
     participants
    0.06
     inclu
    0.06
     barcode
    0.06
     confines
    0.06
    姓名
    0.06
    .flex
    0.06
    Activations Density 0.008%

    No Known Activations