© 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. 55811
    Prev
    Next
    INDEX
    Explanations

    cultural references to community support and 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
    wyn
    -0.06
    amient
    -0.06
    tern
    -0.06
     Bip
    -0.06
    \grid
    -0.06
    rada
    -0.06
     ally
    -0.06
    ÑĢоÑĩ
    -0.06
     Chatt
    -0.06
    èĩ£
    -0.06
    POSITIVE LOGITS
     AABB
    0.07
    ãĥ³ãĤ¬
    0.07
     Imported
    0.06
    illus
    0.06
    ellig
    0.06
     club
    0.06
     community
    0.06
    community
    0.06
    ssel
    0.06
     assim
    0.06
    Activations Density 0.020%

    No Known Activations