© 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. 7824
    Prev
    Next
    INDEX
    Explanations

    future intent

    np_max-act · gemini-2.0-flash

    The neuron is detecting template placeholder tokens (e.g. bracketed metadata fields like “[Your Name]” or header‐id markers) in the text.

    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
     Bul
    -0.06
    _ok
    -0.06
     surrogate
    -0.06
     specs
    -0.06
    439
    -0.06
     advoc
    -0.06
     Німеч
    -0.06
    儿
    -0.06
     columnist
    -0.06
     unanimous
    -0.06
    POSITIVE LOGITS
    (){}↵↵
    0.06
    .EXP
    0.06
     inn
    0.06
     ava
    0.06
     complying
    0.06
    comm
    0.06
     })}↵
    0.06
     WW
    0.06
    :NSLayout
    0.06
    .boolean
    0.06
    Activations Density 0.027%

    No Known Activations