© 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. 14922
    Prev
    Next
    INDEX
    Explanations

    phrases indicating recent performance outcomes in sports

    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
     VÅ¡ech
    -0.08
    .tk
    -0.07
    .setResult
    -0.07
    âr
    -0.07
    ispens
    -0.07
    ảy
    -0.07
    (LP
    -0.06
    objs
    -0.06
    Multiplicity
    -0.06
    .ast
    -0.06
    POSITIVE LOGITS
     having
    0.08
    çļĦæĺ¯
    0.07
    tons
    0.07
    çļĦä¸Ģ个
    0.07
    t
    0.06
     successful
    0.06
    gel
    0.06
     Beste
    0.06
    monds
    0.06
    having
    0.06
    Activations Density 0.007%

    No Known Activations