© 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. 41675
    Prev
    Next
    INDEX
    Explanations

    PLY

    np_max-act · gemini-2.0-flash

    The neuron specifically detects the token marking the end of the assistant’s header (i.e. the boundary token that signals the start of the assistant’s response).

    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
    .cl
    -0.06
    صول
    -0.06
     поход
    -0.06
     conte
    -0.06
     اصل
    -0.06
    FAIL
    -0.06
     undefeated
    -0.06
    Exposed
    -0.06
    vert
    -0.06
     voted
    -0.06
    POSITIVE LOGITS
    __()↵↵
    0.07
    イ
    0.07
     '''
    0.06
     Moines
    0.06
     атмос
    0.06
    '{
    0.06
     grassroots
    0.06
    .ml
    0.06
    icontains
    0.06
     eastern
    0.06
    Activations Density 0.063%

    No Known Activations