© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126827
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the word “writ” (as in “writ of …”) in legal documents.

    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
    ('.')↵
    -0.06
     videoer
    -0.06
    Levels
    -0.06
     метою
    -0.06
     uptake
    -0.06
     qq
    -0.06
    muştur
    -0.06
     değildir
    -0.06
    legacy
    -0.06
    _latency
    -0.06
    POSITIVE LOGITS
     التح
    0.07
     thanking
    0.07
    ellation
    0.07
     cap
    0.07
     Pel
    0.06
    Pieces
    0.06
     Rolling
    0.06
     Inserts
    0.06
    ilarity
    0.06
    otten
    0.06
    Activations Density 0.001%

    No Known Activations