© 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. 119362
    Prev
    Next
    INDEX
    Explanations

    vocabulary related to adaptation and change

    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
    oba
    -0.08
    uelles
    -0.07
    ood
    -0.07
     mand
    -0.07
    mps
    -0.06
    raud
    -0.06
    optic
    -0.06
    álido
    -0.06
    /rfc
    -0.06
    uell
    -0.06
    POSITIVE LOGITS
     accordingly
    0.10
     Accordingly
    0.09
     tactics
    0.09
     Adjust
    0.08
     adjust
    0.08
     adjusts
    0.08
     Tactics
    0.07
     strategies
    0.07
     adjusting
    0.07
    -adjust
    0.07
    Activations Density 0.030%

    No Known Activations