© 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. 12813
    Prev
    Next
    INDEX
    Explanations

    Place names/Locations

    np_max-act · gemini-2.0-flash

    The neuron activates on the title of a work (e.g. the translated name in parentheses), picking out sequences of capitalized title words like “The Man of the Story.”

    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
    Tbl
    -0.07
     Lightweight
    -0.06
     msgs
    -0.06
     français
    -0.06
     Bounty
    -0.06
     PG
    -0.06
     vacations
    -0.06
     |
    -0.06
     REL
    -0.06
    _BR
    -0.06
    POSITIVE LOGITS
    -off
    0.07
    (en
    0.06
    .Mult
    0.06
    福
    0.06
    _campaign
    0.06
    tok
    0.06
    YD
    0.06
    -bot
    0.06
    (args
    0.06
    틀
    0.06
    Activations Density 0.051%

    No Known Activations