© 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. 74796
    Prev
    Next
    INDEX
    Explanations

    Initials

    np_max-act · gemini-2.0-flash

    The neuron activates on short uppercase abbreviations or initials punctuated with periods (e.g. “S.U.”, “F.C.”, “N.G.”).

    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
     ATT
    -0.07
     Microsystems
    -0.06
    	Init
    -0.06
     Esto
    -0.06
    它们
    -0.06
    -mouth
    -0.06
    راه
    -0.06
    938
    -0.05
     armies
    -0.05
     init
    -0.05
    POSITIVE LOGITS
    _amount
    0.07
     Hairst
    0.07
    .J
    0.07
    .credit
    0.07
     Licence
    0.07
    .SE
    0.07
    .Sc
    0.07
     grew
    0.07
    .H
    0.07
    .D
    0.07
    Activations Density 0.020%

    No Known Activations