© 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. 57600
    Prev
    Next
    INDEX
    Explanations

    components of a narrative or summary

    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
    493
    -0.07
    jedn
    -0.07
    ÙİØ©
    -0.07
    inely
    -0.07
     ekip
    -0.06
    )e
    -0.06
     Ø¢ÛĮا
    -0.06
    .Instance
    -0.06
    UTH
    -0.06
    ода
    -0.06
    POSITIVE LOGITS
    CTX
    0.07
     alternative
    0.07
    fram
    0.07
     below
    0.07
    udem
    0.07
     independently
    0.06
     Below
    0.06
    Alternatively
    0.06
     Alternate
    0.06
     reprodu
    0.06
    Activations Density 0.025%

    No Known Activations