© 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. 9-LLAMASCOPE-RES-131K
    11. 94439
    Prev
    Next
    INDEX
    Explanations

    descriptions related to snow and winter landscapes

    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
    award
    -0.06
    aise
    -0.06
    ctl
    -0.06
    reek
    -0.06
    DN
    -0.06
    anium
    -0.06
    reds
    -0.06
     Clayton
    -0.06
    indow
    -0.06
     Inner
    -0.06
    POSITIVE LOGITS
     snow
    0.08
     Snow
    0.06
    Snow
    0.06
    ÐĽÐ¬
    0.06
     winter
    0.06
    vation
    0.06
    OLON
    0.06
    erli
    0.06
     ski
    0.06
    atr
    0.06
    Activations Density 0.017%

    No Known Activations