© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 127586
    Prev
    Next
    INDEX
    Explanations

    words related to natural features or environmental terminology

    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
    йн
    -0.07
     Ambient
    -0.07
    ambient
    -0.07
    ãĢħ
    -0.07
    usi
    -0.06
    UNCH
    -0.06
    pagen
    -0.06
    ello
    -0.06
    eeper
    -0.06
    ween
    -0.06
    POSITIVE LOGITS
    -ÑĤо
    0.06
     fle
    0.06
    æŁ±
    0.06
    Ķ
    0.06
    /tos
    0.06
    -pills
    0.05
    jos
    0.05
     ceremon
    0.05
    nest
    0.05
     licens
    0.05
    Activations Density 0.000%

    No Known Activations