© 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. 16690
    Prev
    Next
    INDEX
    Explanations

    details about navigation and directions

    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
    ä¸ĺ
    -0.07
    avar
    -0.07
    inton
    -0.06
     cit
    -0.06
    ibal
    -0.06
     Roof
    -0.06
     finally
    -0.06
     nowhere
    -0.06
     cites
    -0.06
    eyer
    -0.06
    POSITIVE LOGITS
    richt
    0.07
    left
    0.07
    ãģ£ãģį
    0.06
     richt
    0.06
     Dire
    0.06
    utsch
    0.06
    /left
    0.06
    íļ
    0.06
     LEFT
    0.06
     vou
    0.06
    Activations Density 0.009%

    No Known Activations