© 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. 129385
    Prev
    Next
    INDEX
    Explanations

    references to the act of using something or utility

    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
    .nz
    -0.08
    ร
    -0.08
     usefulness
    -0.08
    à¹Ħว
    -0.08
     useful
    -0.07
    ships
    -0.07
    toi
    -0.07
     usual
    -0.07
    GING
    -0.07
    acades
    -0.07
    POSITIVE LOGITS
    fully
    0.14
    lessly
    0.12
    full
    0.10
    fulness
    0.09
    itarian
    0.09
    ful
    0.09
    åΰçļĦ
    0.08
    age
    0.08
     caution
    0.08
    FUL
    0.08
    Activations Density 0.185%

    No Known Activations