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

    Neuronpedia

    Jacobian LensNEW
    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. 57309
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on the “+” token when it’s used for string or code concatenation.

    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
     saturn
    -0.07
    dif
    -0.07
    scanner
    -0.07
     vari
    -0.07
     Replace
    -0.07
     halo
    -0.07
     Yale
    -0.07
     Лени
    -0.07
    banana
    -0.07
    382
    -0.07
    POSITIVE LOGITS
    realDonaldTrump
    0.06
    ('.'
    0.06
     gost
    0.06
     Herr
    0.06
    :::::|
    0.06
     "\\"
    0.06
    .='
    0.06
     ایست
    0.06
    ']."
    0.06
     potrze
    0.06
    Activations Density 0.016%

    No Known Activations