© 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. 76549
    Prev
    Next
    INDEX
    Explanations

    instances of unique or extraordinary expressions and community engagements

    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
    utow
    -0.07
    zell
    -0.06
    AMI
    -0.06
    essel
    -0.06
    ucz
    -0.06
    inski
    -0.06
    esser
    -0.06
    reeze
    -0.06
    licated
    -0.06
    erte
    -0.05
    POSITIVE LOGITS
    à¹Įà¹Ģà¸ŀ
    0.08
     Äijá»ĥ
    0.08
    via
    0.07
    691
    0.07
     inorder
    0.07
    692
    0.07
    opens
    0.07
    ForResult
    0.07
    661
    0.07
     أجÙĦ
    0.07
    Activations Density 0.003%

    No Known Activations