© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7066
    Prev
    Next
    INDEX
    Explanations

    /LICENSE

    np_max-act · gemini-2.0-flash

    The neuron fires on license‐header or license‐URL tokens (e.g. occurrences of “LICENSE” in a software license declaration).

    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
     Wooden
    -0.07
    	push
    -0.06
    fection
    -0.06
    incip
    -0.06
    ikan
    -0.06
    .expect
    -0.06
     Degree
    -0.06
    -backend
    -0.06
     analytic
    -0.06
    oodoo
    -0.06
    POSITIVE LOGITS
    @Enable
    0.06
     aDecoder
    0.06
    >
    
    ↵
    0.06
    .bp
    0.06
     DHS
    0.06
    ./(
    0.06
     Ens
    0.06
     merch
    0.06
    ệ
    0.06
    ùy
    0.06
    Activations Density 0.001%

    No Known Activations