© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 82728
    Prev
    Next
    INDEX
    Explanations

    content related to food preparation and cooking guidelines

    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
    odate
    -0.07
    bie
    -0.06
    ypsum
    -0.06
    lius
    -0.06
    DateString
    -0.06
     Duty
    -0.06
    yš
    -0.06
    eer
    -0.06
    inth
    -0.06
     éĸ¢éĢ£
    -0.06
    POSITIVE LOGITS
    #Region
    0.07
    ìĦ±
    0.07
    ([]*
    0.07
     âĻ
    0.06
    -order
    0.06
    IMIT
    0.06
     order
    0.06
    /up
    0.06
     ++$
    0.06
    Mocks
    0.06
    Activations Density 0.013%

    No Known Activations