© 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. 38684
    Prev
    Next
    INDEX
    Explanations

    chemical/gene identifiers

    np_max-act · gemini-2.0-flash

    The neuron activates on placeholder entity tokens of the form “NAME_<number>,” i.e. it detects occurrences of indexed NAME_ tokens.

    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
    chodu
    -0.06
    طار
    -0.06
    _energy
    -0.06
    ultan
    -0.06
    aign
    -0.06
     Bě
    -0.06
    uf
    -0.06
    煤
    -0.06
     Train
    -0.06
    िछल
    -0.05
    POSITIVE LOGITS
    Pixels
    0.07
     x
    0.07
    尽管
    0.06
     punctuation
    0.06
     scp
    0.06
     makes
    0.06
    _TIMES
    0.06
     Send
    0.06
     outcry
    0.06
    .nanoTime
    0.06
    Activations Density 0.040%

    No Known Activations