© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55512
    Prev
    Next
    INDEX
    Explanations

    Writing and comments

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the word “response” (and closely related discussion of response formatting) in instruction 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
     smashed
    -0.06
     autobiography
    -0.06
     Lawyer
    -0.06
    .setTimeout
    -0.06
     animal
    -0.06
    (View
    -0.06
    _mobile
    -0.06
    登録
    -0.06
     tn
    -0.06
    華
    -0.06
    POSITIVE LOGITS
    остат
    0.08
     vibr
    0.07
     CCS
    0.07
     Nur
    0.07
    wi
    0.06
     akşam
    0.06
     》
    0.06
    'nda
    0.06
    Adv
    0.06
    logger
    0.06
    Activations Density 0.036%

    No Known Activations