© 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. 126052
    Prev
    Next
    INDEX
    Explanations

    200, 201 (numbers)

    np_max-act · gemini-2.0-flash

    legal case citations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on numeric tokens representing years (particularly four-digit years in legal citations).

    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
    Rocket
    -0.06
    Tell
    -0.06
    >b
    -0.06
     sniper
    -0.06
     Nacht
    -0.06
     punishable
    -0.06
     unknow
    -0.06
    บ
    -0.06
     سي
    -0.06
    हम
    -0.06
    POSITIVE LOGITS
    .bool
    0.07
    _params
    0.07
     انگلیسی
    0.07
     php
    0.07
    )")↵
    0.06
    ]**
    0.06
    )**
    0.06
     malaysia
    0.06
     Mods
    0.06
    cantidad
    0.06
    Activations Density 0.006%

    No Known Activations