© 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. 9-LLAMASCOPE-RES-131K
    11. 96578
    Prev
    Next
    INDEX
    Explanations

    terms related to fishing, specifically highlighting techniques and equipment

    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
     Fate
    -0.06
    zell
    -0.06
    arse
    -0.06
     Hlav
    -0.06
    vron
    -0.06
    emarks
    -0.05
     conference
    -0.05
    ean
    -0.05
    etch
    -0.05
     winds
    -0.05
    POSITIVE LOGITS
    uide
    0.07
    osta
    0.07
    allel
    0.07
    roke
    0.07
    OTH
    0.07
    .Std
    0.07
    ÏĦÏī
    0.07
    ibil
    0.07
     sond
    0.06
    anik
    0.06
    Activations Density 0.002%

    No Known Activations