© 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. 119138
    Prev
    Next
    INDEX
    Explanations

    groups or classifications within a larger context

    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
    íĮħ
    -0.08
    opus
    -0.08
    .ham
    -0.07
    kova
    -0.07
    ogui
    -0.07
    롱
    -0.07
    jeme
    -0.07
     BAÅŀ
    -0.07
    kili
    -0.07
    ngine
    -0.07
    POSITIVE LOGITS
     ones
    0.08
     folks
    0.07
     typ
    0.07
     category
    0.07
     toward
    0.06
     approach
    0.06
     type
    0.06
     reconc
    0.06
     subs
    0.06
     who
    0.06
    Activations Density 0.009%

    No Known Activations