© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 128385
    Prev
    Next
    INDEX
    Explanations

    aiming devices

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of optical aiming devices (e.g. “sights,” “scopes,” “optical,” “electro‐optical,” “reticle,” etc.).

    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
    νομα
    -0.07
    за
    -0.06
     wäre
    -0.06
     Pru
    -0.06
    utt
    -0.06
    		↵	↵
    -0.06
     penetr
    -0.06
    _scr
    -0.06
    _post
    -0.06
     Testament
    -0.06
    POSITIVE LOGITS
    Captain
    0.07
    <num
    0.06
     modular
    0.06
     Amnesty
    0.06
    /gtest
    0.06
     playful
    0.06
    	File
    0.06
     BUSINESS
    0.06
     Conversely
    0.06
     clearInterval
    0.06
    Activations Density 0.006%

    No Known Activations