© 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. 22-LLAMASCOPE-RES-131K
    11. 3846
    Prev
    Next
    INDEX
    Explanations

    references to small or diminutive characteristics

    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
     HRESULT
    -0.06
    dat
    -0.06
    449
    -0.06
    al
    -0.05
     fewer
    -0.05
    i
    -0.05
    ses
    -0.05
     various
    -0.05
    od
    -0.05
    aran
    -0.05
    POSITIVE LOGITS
    -scale
    0.10
    /tiny
    0.10
    -sized
    0.09
    -small
    0.09
    .scalablytyped
    0.09
    @nate
    0.08
    /small
    0.08
    دÛĮگر
    0.08
    OffsetTable
    0.07
    ï½į
    0.07
    Activations Density 0.030%

    No Known Activations