© 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. 29871
    Prev
    Next
    INDEX
    Explanations

    peptide

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “peptide” (including variants such as “Peptide” and “peptide-”), thus detecting mentions of peptides.

    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
    "W
    -0.07
     círk
    -0.06
    ChildScrollView
    -0.06
    534
    -0.06
    �
    -0.06
    owers
    -0.06
     Zh
    -0.06
     Churches
    -0.06
     Schwartz
    -0.06
     furthermore
    -0.06
    POSITIVE LOGITS
     peptide
    0.15
     peptides
    0.14
    ptides
    0.10
     depleted
    0.08
    ptide
    0.08
     Pe
    0.08
     pleas
    0.07
    .gui
    0.07
    aoke
    0.07
    Deg
    0.07
    Activations Density 0.006%

    No Known Activations