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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90913
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron never activates on any of the input tokens—it doesn’t respond to any detectable pattern.

    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
    ulates
    -0.07
     ""},↵
    -0.06
    undles
    -0.06
    ternal
    -0.06
     PCs
    -0.06
    .mask
    -0.06
     conseils
    -0.06
     graft
    -0.06
     pedigree
    -0.05
    quares
    -0.05
    POSITIVE LOGITS
    isen
    0.07
     chiff
    0.07
     (~
    0.07
    :create
    0.06
     Fem
    0.06
     knot
    0.06
     nákup
    0.06
     вниз
    0.06
    Truthy
    0.06
    وال
    0.06
    Activations Density 0.004%

    No Known Activations