© 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 EvalsExportsinterp-engineNEWAPI 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. 27223
    Prev
    Next
    INDEX
    Explanations

    the word "any" in various contexts

    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
    ulle
    -0.07
    acus
    -0.07
    urovision
    -0.07
     respectively
    -0.07
     же
    -0.07
    airo
    -0.07
     respective
    -0.07
    yper
    -0.07
    amiliar
    -0.06
    ì°©
    -0.06
    POSITIVE LOGITS
    æŶåĢĻ
    0.07
    Ìģ
    0.07
    /catalog
    0.07
    times
    0.06
    Ñī
    0.06
    ëŀĺ
    0.06
    where
    0.06
    wh
    0.06
    stead
    0.06
    tl
    0.06
    Activations Density 0.006%

    No Known Activations