© 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 EvalsExportsinterp-engineNEWAPI 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. 15-RESID-POST-AA
    11. 34806
    Prev
    Next
    INDEX
    Explanations

    business and technical descriptions

    np_max-act · gemini-2.0-flash

    the neuron detects tokens that are parts of hyphenated or compound words—especially technical compound nouns (e.g., front-end, information-sharing, call-stack).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _:
    -0.06
     unlock
    -0.06
    ıp
    -0.06
     fab
    -0.06
     Css
    -0.06
     /:
    -0.06
     rewind
    -0.06
    hel
    -0.06
     ullam
    -0.05
     probs
    -0.05
    POSITIVE LOGITS
    -P
    0.11
    -d
    0.11
    -A
    0.11
    -C
    0.11
    -D
    0.11
    -N
    0.11
    -c
    0.11
    -F
    0.10
    -Z
    0.10
    -a
    0.10
    Activations Density 1.156%

    No Known Activations