© 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. 105009
    Prev
    Next
    INDEX
    Explanations

    numerical rankings and positions related to competitive 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
     Fund
    -0.08
    fund
    -0.07
     fund
    -0.07
    urat
    -0.07
    ambi
    -0.07
    нÑĤ
    -0.07
    ako
    -0.07
    eniable
    -0.06
    insky
    -0.06
     Opport
    -0.06
    POSITIVE LOGITS
     start
    0.07
     Burr
    0.07
     front
    0.07
    rol
    0.06
    wr
    0.06
    Start
    0.06
     Start
    0.06
    -start
    0.06
    _START
    0.06
    initial
    0.06
    Activations Density 0.014%

    No Known Activations