© 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. 2589
    Prev
    Next
    INDEX
    Explanations

    references to commentary or reactions from various sources

    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
    ayne
    -0.09
    omik
    -0.08
    imits
    -0.08
    омен
    -0.08
    ekli
    -0.08
    ramer
    -0.07
    ánt
    -0.07
    ør
    -0.07
     éĢļ
    -0.07
    enou
    -0.07
    POSITIVE LOGITS
     both
    0.09
     quarters
    0.08
     members
    0.07
     across
    0.07
     everywhere
    0.07
    both
    0.06
     some
    0.06
     constituents
    0.06
     others
    0.06
    zes
    0.06
    Activations Density 0.032%

    No Known Activations