© 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. 14869
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to societal and environmental factors

    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
    pagesize
    -0.06
    isan
    -0.06
     a
    -0.06
     respective
    -0.06
    ellan
    -0.06
    prep
    -0.06
    itura
    -0.06
    erval
    -0.06
    iko
    -0.06
    coe
    -0.06
    POSITIVE LOGITS
     nÃło
    0.11
    VICE
    0.09
     olursa
    0.08
    centage
    0.07
    .desktop
    0.07
    accom
    0.07
     mÃł
    0.07
    à¹Ħหà¸Ļ
    0.07
    apes
    0.06
    ToProps
    0.06
    Activations Density 0.019%

    No Known Activations