© 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. 118879
    Prev
    Next
    INDEX
    Explanations

    elements related to interaction and connection with local communities

    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
    enor
    -0.07
    EPS
    -0.07
    ï¸
    -0.07
    ìŀIJê°Ģ
    -0.07
    661
    -0.07
    xygen
    -0.07
    олом
    -0.07
    ÑĮко
    -0.07
    iná
    -0.07
    ingham
    -0.07
    POSITIVE LOGITS
     local
    0.13
     locals
    0.12
    local
    0.10
     locally
    0.10
    locals
    0.10
     native
    0.08
     host
    0.08
    (local
    0.08
     yerel
    0.07
    /local
    0.07
    Activations Density 0.070%

    No Known Activations