© 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. 126853
    Prev
    Next
    INDEX
    Explanations

    references to community structure or organization

    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
     ObjectType
    -0.07
    GRES
    -0.06
    terra
    -0.06
    151
    -0.06
    ãĥªãĥ¼
    -0.06
    /cop
    -0.06
    ijken
    -0.06
    èįī
    -0.06
    259
    -0.06
    ä»Ģä¹Ī
    -0.06
    POSITIVE LOGITS
     they
    0.07
    quist
    0.06
     we
    0.06
     these
    0.06
    onian
    0.06
    Blocking
    0.06
    caf
    0.06
     kå
    0.06
    ÐķТ
    0.06
    ework
    0.06
    Activations Density 0.011%

    No Known Activations