© 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. 126604
    Prev
    Next
    INDEX
    Explanations

    Diverse text snippets

    np_max-act · gemini-2.0-flash

    This neuron detects special internal format tokens (like <|start_header_id|>, <|end_header_id|>, and <|eot_id|>) used to mark headers and message boundaries in the document.

    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
     Communist
    -0.07
    agic
    -0.07
     preschool
    -0.07
     Wyoming
    -0.07
     Executor
    -0.07
     aest
    -0.06
    (each
    -0.06
     supplement
    -0.06
    .SH
    -0.06
    lifting
    -0.06
    POSITIVE LOGITS
    >Note
    0.07
     Ні
    0.06
     verd
    0.06
     ")");↵
    0.06
    github
    0.06
     weiber
    0.06
     электри
    0.06
    _typeDefinitionSize
    0.06
    .WriteHeader
    0.06
    ’n
    0.06
    Activations Density 0.048%

    No Known Activations