© 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. 123703
    Prev
    Next
    INDEX
    Explanations

    chemical elements and compounds, particularly related to rare-earth metals

    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
    ahat
    -0.08
    hift
    -0.08
    uju
    -0.07
    že
    -0.07
    елик
    -0.07
    phies
    -0.07
    bsd
    -0.07
    èĻŁ
    -0.07
    issance
    -0.07
    oodoo
    -0.07
    POSITIVE LOGITS
    /Math
    0.07
    ÅĻÃŃz
    0.07
     SPDX
    0.06
     rich
    0.06
     اÙĦاع
    0.06
    -rich
    0.06
    ÑĦоÑĢма
    0.06
     Rich
    0.06
     Formal
    0.06
    ÑĥÑĪ
    0.06
    Activations Density 0.026%

    No Known Activations