© 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 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. 17-LLAMASCOPE-RES-131K
    11. 56087
    Prev
    Next
    INDEX
    Explanations

    references to "soft" and related terms

    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
    redient
    -0.08
    itious
    -0.08
    .scalablytyped
    -0.08
    andest
    -0.07
    icensed
    -0.07
    lectic
    -0.07
    stag
    -0.07
    paid
    -0.06
    naments
    -0.06
    herit
    -0.06
    POSITIVE LOGITS
    ening
    0.13
    wares
    0.12
    ness
    0.11
    ened
    0.11
     mại
    0.09
    eners
    0.09
    ies
    0.09
     Soft
    0.09
    ener
    0.08
    soft
    0.08
    Activations Density 0.011%

    No Known Activations