© 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. 59673
    Prev
    Next
    INDEX
    Explanations

    references to specific resources or creations related to literature and cultural heritage

    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
    rike
    -0.07
    -0.06
     Ply
    -0.06
     for
    -0.06
     Counts
    -0.06
     (
    -0.06
     comb
    -0.05
    ers
    -0.05
     whose
    -0.05
    ee
    -0.05
    POSITIVE LOGITS
    lbrace
    0.08
    اÙĤع
    0.07
    лага
    0.07
    .getInteger
    0.07
     pob
    0.07
    .easing
    0.07
    ãĤ¡
    0.07
    CCA
    0.07
    ê´
    0.07
    .ol
    0.07
    Activations Density 0.000%

    No Known Activations