© 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. 29486
    Prev
    Next
    INDEX
    Explanations

    references to social or support groups

    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
    ushman
    -0.09
    ẽ
    -0.08
    achel
    -0.07
    /frame
    -0.07
    amedi
    -0.07
     GenerationType
    -0.07
    /filepath
    -0.07
    endas
    -0.07
    ihan
    -0.07
    loo
    -0.07
    POSITIVE LOGITS
     membership
    0.09
     members
    0.08
     formed
    0.08
     memberships
    0.07
     activity
    0.07
     groups
    0.07
    æĪIJåijĺ
    0.07
     activities
    0.07
     meetings
    0.07
    èĮ¨
    0.06
    Activations Density 0.037%

    No Known Activations