© 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. 89361
    Prev
    Next
    INDEX
    Explanations

    numeric data and dates

    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
    ersen
    -0.07
    incare
    -0.07
    antz
    -0.06
    IFEST
    -0.06
    ewire
    -0.06
    ewise
    -0.06
     dau
    -0.06
    edic
    -0.06
    otherapy
    -0.06
    -mf
    -0.06
    POSITIVE LOGITS
    URI
    0.07
     permanently
    0.06
     research
    0.06
     Blacks
    0.06
    962
    0.06
     Research
    0.06
    ãģ«ãģ¤
    0.06
     transl
    0.06
    _atual
    0.06
    mits
    0.06
    Activations Density 0.012%

    No Known Activations