© 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. 43440
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    The neuron detects discourse-level transition markers (e.g. “Firstly,” “Secondly,” “Finally,” “Additionally,” etc.) that signal sequential or additive steps.

    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
    _GAP
    -0.07
     deck
    -0.07
    _invalid
    -0.07
     funk
    -0.06
    ighborhood
    -0.06
    Credential
    -0.06
    .market
    -0.06
     ****
    -0.06
     humane
    -0.06
    _eth
    -0.06
    POSITIVE LOGITS
     समस
    0.07
    �
    0.07
     stør
    0.07
    지원
    0.07
    활동
    0.06
     tốt
    0.06
     karena
    0.06
     Soviets
    0.06
     HOLD
    0.06
     darm
    0.06
    Activations Density 0.281%

    No Known Activations