© 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. 75291
    Prev
    Next
    INDEX
    Explanations

    phrases related to food and dining experiences

    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
    odash
    -0.07
    idders
    -0.06
    oubles
    -0.06
    acher
    -0.06
    éĢ¸
    -0.06
    atcher
    -0.06
    eldom
    -0.06
    udiant
    -0.06
    importe
    -0.06
    itters
    -0.06
    POSITIVE LOGITS
    exe
    0.07
    ẩy
    0.07
    Ñĩил
    0.07
     sorte
    0.07
    ologue
    0.07
     наÑģÑĤ
    0.06
    女åŃIJ
    0.06
     CAUSED
    0.06
    .AttributeSet
    0.06
    TINGS
    0.06
    Activations Density 0.014%

    No Known Activations