© 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. 126012
    Prev
    Next
    INDEX
    Explanations

    Forum content

    np_max-act · gemini-2.0-flash

    The neuron fires on special structural tokens and numeric indicators that mark conversation boundaries (e.g. header/footer delimiters and turn‐index numbers).

    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
     hjem
    -0.06
    _Store
    -0.06
    ває
    -0.06
    ‌است
    -0.06
    -sk
    -0.06
    ense
    -0.06
    imps
    -0.06
    pcodes
    -0.06
    aliz
    -0.06
    asje
    -0.06
    POSITIVE LOGITS
     toxicity
    0.07
    344
    0.07
     Construct
    0.07
    :',↵
    0.06
    "};↵↵
    0.06
     가입
    0.06
     chết
    0.06
     =↵↵
    0.06
    ,),↵
    0.06
    <s
    0.06
    Activations Density 0.088%

    No Known Activations