© 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. 15-LLAMASCOPE-RES-131K
    11. 26963
    Prev
    Next
    INDEX
    Explanations

    references to proposed methodologies and their significance in research contexts

    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
    anta
    -0.07
    _legend
    -0.07
    heimer
    -0.07
    IMIT
    -0.06
    ationship
    -0.06
    legend
    -0.06
    apper
    -0.06
    acades
    -0.06
    пиÑģок
    -0.06
    zie
    -0.06
    POSITIVE LOGITS
     tool
    0.07
     factor
    0.07
     viable
    0.06
     valid
    0.06
    ayette
    0.06
    tool
    0.06
     source
    0.06
    .Std
    0.06
     option
    0.06
     str
    0.06
    Activations Density 0.034%

    No Known Activations