© 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. 5191
    Prev
    Next
    INDEX
    Explanations

    biochemical terms and gene-related markers in metabolic processes

    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
    icari
    -0.08
    xfff
    -0.07
    PointF
    -0.07
    ίÏĦ
    -0.07
    esub
    -0.07
    ByUrl
    -0.06
    avid
    -0.06
     ilet
    -0.06
    aver
    -0.06
     ТомÑĥ
    -0.06
    POSITIVE LOGITS
    ipeg
    0.07
     RuntimeObject
    0.07
    ,↵↵
    0.06
    âĢ¦↵↵
    0.06
     ‘
    0.06
     whose
    0.06
    ALTH
    0.06
    isContained
    0.06
     âĢ¦↵↵
    0.06
     вз
    0.06
    Activations Density 0.072%

    No Known Activations