© 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. 55417
    Prev
    Next
    INDEX
    Explanations

    maintaining a position

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric measurement phrases—especially time‐duration expressions (e.g. “maintained for a period of eight hours to two days”).

    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
    iltr
    -0.06
    _NS
    -0.06
     Shirley
    -0.06
    aysia
    -0.06
     suicide
    -0.06
     transporter
    -0.06
    ascal
    -0.06
     trainers
    -0.06
    train
    -0.06
    CEO
    -0.06
    POSITIVE LOGITS
     соч
    0.07
    urable
    0.06
    leftright
    0.06
    ]bool
    0.06
    ieval
    0.06
    agens
    0.06
     lå
    0.06
    .log
    0.06
     Ancient
    0.06
     тру
    0.06
    Activations Density 0.031%

    No Known Activations