© 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. 128889
    Prev
    Next
    INDEX
    Explanations

    actions related to organizing and managing tasks or items

    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
    ,
    -0.06
     homeland
    -0.06
     poles
    -0.05
    kal
    -0.05
     nomin
    -0.05
    _CLEAN
    -0.05
     besides
    -0.05
     dil
    -0.05
    /
    -0.05
    tim
    -0.05
    POSITIVE LOGITS
     Compact
    0.10
     compact
    0.09
    Compact
    0.08
    compact
    0.08
    xCC
    0.07
     tamp
    0.07
    ocs
    0.07
    sockopt
    0.07
    елик
    0.07
    ëĵ¯
    0.07
    Activations Density 0.018%

    No Known Activations