© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 57970
    Prev
    Next
    INDEX
    Explanations

    numerical references or indicators, possibly related to pagination or ordering

    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
    ãģŁãģĦ
    -0.07
    #endregion
    -0.06
    ynes
    -0.06
    utsch
    -0.06
    534
    -0.06
    ê·ľ
    -0.06
    lej
    -0.06
    raison
    -0.06
    ìĦ¼
    -0.06
    apon
    -0.06
    POSITIVE LOGITS
     Rach
    0.07
    rende
    0.07
    /etc
    0.07
     Yer
    0.07
    VERR
    0.06
     åıĮ线
    0.06
     Candid
    0.06
    ache
    0.06
    opa
    0.06
    op
    0.06
    Activations Density 0.000%

    No Known Activations