© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 12812
    Prev
    Next
    INDEX
    Explanations

    adjacency

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of graph-theoretic parameters (like girth, number of vertices, edges, minimum degree, etc.).

    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
     Italia
    -0.06
    umptech
    -0.06
     Orch
    -0.06
     Fathers
    -0.06
     Covers
    -0.06
    _agents
    -0.06
     FormControl
    -0.06
     dumping
    -0.06
     icons
    -0.06
     JJ
    -0.06
    POSITIVE LOGITS
    izes
    0.07
    izophren
    0.07
     strate
    0.07
     lorsque
    0.06
    อนด
    0.06
    (pow
    0.06
    важ
    0.06
     Evrop
    0.06
     mie
    0.06
     sessiz
    0.06
    Activations Density 0.008%

    No Known Activations