© 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. 29151
    Prev
    Next
    INDEX
    Explanations

    references to quantity or frequency regarding firms or entities

    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
     Resolution
    -0.07
     Needle
    -0.06
    iple
    -0.06
    ién
    -0.06
    kc
    -0.06
    iliz
    -0.06
    ucer
    -0.05
     Neutral
    -0.05
    egov
    -0.05
    ¸
    -0.05
    POSITIVE LOGITS
    interop
    0.08
     Graves
    0.07
     JsonRequest
    0.07
    icone
    0.07
    ikip
    0.07
    pill
    0.06
    ominator
    0.06
    ANJI
    0.06
    icity
    0.06
    _WS
    0.06
    Activations Density 0.007%

    No Known Activations