© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 42851
    Prev
    Next
    INDEX
    Explanations

    online forum questions

    np_max-act · gemini-2.0-flash

    This neuron detects meta-comments about asking or posting the question (e.g. words like “asked,” “question,” “posted,” and references to forums).

    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
     psych
    -0.07
     HM
    -0.07
     blind
    -0.07
     fixture
    -0.06
     א
    -0.06
    (cls
    -0.06
    ़्
    -0.06
     виконав
    -0.06
     Sed
    -0.06
    .mm
    -0.06
    POSITIVE LOGITS
    Cash
    0.06
    Vertical
    0.06
    FieldValue
    0.06
    _posts
    0.06
     فرودگاه
    0.06
    _DRIVER
    0.06
     افر
    0.06
    $user
    0.06
     distributes
    0.06
     WaitFor
    0.06
    Activations Density 0.016%

    No Known Activations