© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 74704
    Prev
    Next
    INDEX
    Explanations

    Scientific and mathematical descriptions

    np_max-act · gemini-2.0-flash

    The neuron activates on technical terms related to diffusion processes (e.g. particle, motion, randomly, diffusion, stable, system).

    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
    (infile
    -0.07
    419
    -0.07
    sort
    -0.07
     weary
    -0.07
    FK
    -0.06
     Hv
    -0.06
    GO
    -0.06
     Ike
    -0.06
     немає
    -0.06
    .Lerp
    -0.06
    POSITIVE LOGITS
     Facing
    0.09
     cricket
    0.06
    -carousel
    0.06
    .lines
    0.06
     disclosing
    0.06
     陳
    0.06
     Comparison
    0.06
     chocolate
    0.06
     btn
    0.06
    AppBar
    0.06
    Activations Density 0.017%

    No Known Activations