© 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. 84107
    Prev
    Next
    INDEX
    Explanations

    references to academic rankings and institution performance

    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
    .sul
    -0.07
    пÑĢимеÑĢ
    -0.07
     дел
    -0.07
    ~↵
    -0.06
    isay
    -0.06
     enc
    -0.06
    amax
    -0.06
    OSE
    -0.06
     ÑĢеÑģ
    -0.06
    otte
    -0.06
    POSITIVE LOGITS
     Overall
    0.07
    overall
    0.07
    sen
    0.07
    ìĥģìľĦ
    0.06
     Boeh
    0.06
     tied
    0.06
    iben
    0.06
    Overall
    0.06
    ipt
    0.06
    ÑĥÑĤи
    0.06
    Activations Density 0.004%

    No Known Activations