© 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. 110131
    Prev
    Next
    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash

    The neuron activates on numbered list markers (e.g. the “1.” or “1)” tokens indicating list items).

    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
    пион
    -0.06
     pulses
    -0.06
     superb
    -0.06
    imulation
    -0.06
    -split
    -0.06
    окон
    -0.06
    σή
    -0.06
     stimulation
    -0.06
     analytic
    -0.06
     champions
    -0.06
    POSITIVE LOGITS
    templ
    0.06
    -encoded
    0.06
    ']):↵
    0.06
    \Category
    0.06
     مذه
    0.06
    A
    0.06
    According
    0.06
     права
    0.06
     手机
    0.06
    .matches
    0.06
    Activations Density 0.065%

    No Known Activations