© 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. 90245
    Prev
    Next
    INDEX
    Explanations

    organizations, events, and various entities associated with collaborative and educational activities

    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
    senal
    -0.07
    /null
    -0.06
    ï
    -0.06
    uien
    -0.06
    angan
    -0.06
     recip
    -0.06
    anj
    -0.06
    ahead
    -0.06
    ardless
    -0.06
    -fe
    -0.06
    POSITIVE LOGITS
    okoj
    0.07
    cluding
    0.07
     including
    0.07
    ijken
    0.07
    alion
    0.06
     Aires
    0.06
    including
    0.06
     AIS
    0.06
     vÄįetnÄĽ
    0.06
    ÑĢÑĥд
    0.06
    Activations Density 0.023%

    No Known Activations