© 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. 123990
    Prev
    Next
    INDEX
    Explanations

    quantitative metrics and comparisons related to medical and economic 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
    ystick
    -0.09
    LOAT
    -0.08
    egas
    -0.08
    argest
    -0.08
    loat
    -0.07
     derece
    -0.07
    hiba
    -0.07
    oldt
    -0.07
    iable
    -0.07
    Ãłng
    -0.07
    POSITIVE LOGITS
    /high
    0.09
     due
    0.07
     syndrome
    0.06
    ãĢģé«ĺ
    0.06
     Syndrome
    0.06
    ÑĢаб
    0.06
     Bale
    0.05
    -low
    0.05
     caused
    0.05
    due
    0.05
    Activations Density 0.079%

    No Known Activations