© 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. 56242
    Prev
    Next
    INDEX
    Explanations

    references to organizations and initiatives that provide support and relief to 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
    isure
    -0.07
    anko
    -0.07
    UED
    -0.06
    .bunifuFlatButton
    -0.06
    Routine
    -0.06
    uty
    -0.06
    ayo
    -0.06
    umbo
    -0.06
    ucus
    -0.06
    à¸ĩà¸Ħ
    -0.06
    POSITIVE LOGITS
     programs
    0.10
     Programs
    0.09
     organization
    0.08
    programs
    0.07
     programas
    0.07
    rganization
    0.07
    .vol
    0.07
     organisation
    0.07
     activities
    0.07
     ï½ľ
    0.07
    Activations Density 0.057%

    No Known Activations