© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 31083
    Prev
    Next
    INDEX
    Explanations

    mentions of staff or team members in various 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
    GRES
    -0.08
    fell
    -0.08
    ós
    -0.08
    оÑģ
    -0.08
    aber
    -0.07
    iltr
    -0.07
    omb
    -0.07
    -era
    -0.07
    ian
    -0.07
    /stats
    -0.07
    POSITIVE LOGITS
     who
    0.08
    hips
    0.08
    hip
    0.08
    lease
    0.07
    chaft
    0.07
    hood
    0.07
    ials
    0.07
    errupted
    0.07
    ìī
    0.07
     whom
    0.07
    Activations Density 0.014%

    No Known Activations