© 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. 14614
    Prev
    Next
    INDEX
    Explanations

    references to visual media content and additional resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Web navigation instructions that direct users how to interact with page elements to access additional content or functionality.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    issing
    -0.07
    .blob
    -0.07
     Crown
    -0.06
    784
    -0.06
    umb
    -0.06
     Murdoch
    -0.06
    ÑģÑĤÑĢ
    -0.06
     occasions
    -0.06
     Lob
    -0.06
    unde
    -0.06
    POSITIVE LOGITS
    ÑĭÑĪ
    0.07
    stant
    0.07
    cona
    0.07
    vant
    0.07
    idot
    0.07
    寶
    0.06
    umatic
    0.06
    zan
    0.06
    PIP
    0.06
    sb
    0.06
    Activations Density 0.017%

    No Known Activations