© 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. 13545
    Prev
    Next
    INDEX
    Explanations

    on/off

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the phrase “on and off” (including hyphenated or reversed variants) indicating intermittent or sporadic activity.

    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
    mark
    -0.08
    排名
    -0.06
    unakan
    -0.06
    інг
    -0.06
     Hindu
    -0.06
    От
    -0.06
    、本
    -0.06
    ández
    -0.06
    Europe
    -0.06
     QApplication
    -0.06
    POSITIVE LOGITS
     gift
    0.07
     امیر
    0.07
     amend
    0.07
     acknowledgment
    0.06
    =fopen
    0.06
    Mathf
    0.06
    adies
    0.06
     fırsat
    0.06
     selfish
    0.06
    �新
    0.06
    Activations Density 0.018%

    No Known Activations