© 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. 15-LLAMASCOPE-RES-131K
    11. 86758
    Prev
    Next
    INDEX
    Explanations

    references to change and adaptation in various 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
    ÑĸÑģно
    -0.07
     hann
    -0.07
    esium
    -0.06
    erate
    -0.06
    ongan
    -0.06
     counter
    -0.06
    .obtain
    -0.06
    illion
    -0.06
    ifton
    -0.06
    avar
    -0.06
    POSITIVE LOGITS
    433
    0.07
    帯
    0.06
    ãģªãģĮãĤī
    0.06
     Rarity
    0.06
     뼰
    0.06
     unprecedented
    0.06
     SEQ
    0.06
     serving
    0.06
    İ·
    0.06
    ä¸ĸç´Ģ
    0.06
    Activations Density 0.005%

    No Known Activations