© 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. 931
    Prev
    Next
    INDEX
    Explanations

    tradition

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “tradition” (and its plural “traditions”).

    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
    Spatial
    -0.08
     chew
    -0.07
    '));↵
    -0.07
    Cell
    -0.07
    pure
    -0.07
     pure
    -0.06
    UTERS
    -0.06
    look
    -0.06
    -life
    -0.06
     Hashtable
    -0.06
    POSITIVE LOGITS
     traditions
    0.11
     tradition
    0.11
     Tradition
    0.08
     customs
    0.08
    俗
    0.07
     συν
    0.07
     Dân
    0.07
     conventions
    0.07
     SHALL
    0.07
     periodically
    0.07
    Activations Density 0.008%

    No Known Activations