© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 93571
    Prev
    Next
    INDEX
    Explanations

    numerals and numerical values related to software versions and travel data

    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
     dilig
    -0.08
    alborg
    -0.07
    eyh
    -0.07
    کرÛĮ
    -0.07
    овиÑĩ
    -0.07
    .MixedReality
    -0.07
    xbf
    -0.06
    DBG
    -0.06
    fld
    -0.06
    .units
    -0.06
    POSITIVE LOGITS
    omm
    0.07
    OA
    0.06
     Spor
    0.06
    uds
    0.06
    ience
    0.06
    OTTOM
    0.06
     Arnold
    0.05
    isa
    0.05
    ogene
    0.05
    uy
    0.05
    Activations Density 0.006%

    No Known Activations