© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 83178
    Prev
    Next
    INDEX
    Explanations

    references to controversial or provocative pop culture figures and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    egin
    -0.07
    emetery
    -0.07
    odyn
    -0.06
    velt
    -0.06
    ospace
    -0.06
    IPA
    -0.06
    ment
    -0.06
     Mate
    -0.06
    รà¸Ķ
    -0.06
    "struct
    -0.06
    POSITIVE LOGITS
     persona
    0.07
     merch
    0.07
     stage
    0.06
    šen
    0.06
    ppe
    0.06
     hiatus
    0.06
    ãĥ¼ãĥŀ
    0.06
    image
    0.06
     tez
    0.06
    uniform
    0.06
    Activations Density 0.024%

    No Known Activations