© 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. 12744
    Prev
    Next
    INDEX
    Explanations

    separators

    np_max-act · gemini-2.0-flash

    The neuron is specialized to pick out numeric tokens (e.g. decimal numbers) in the text.

    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
    	reload
    -0.06
    	run
    -0.06
     Trials
    -0.06
     Pending
    -0.06
     stretching
    -0.06
    /ip
    -0.06
     Appliances
    -0.06
    сього
    -0.06
    	Result
    -0.06
    ’é
    -0.06
    POSITIVE LOGITS
     ре
    0.07
    otland
    0.07
    apeut
    0.07
     sarc
    0.06
     unlink
    0.06
    mma
    0.06
    Link
    0.06
     redd
    0.06
     इत
    0.06
    .Helpers
    0.06
    Activations Density 0.006%

    No Known Activations