© 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. 16478
    Prev
    Next
    INDEX
    Explanations

    terms related to the fishing industry

    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
    /trunk
    -0.07
     Sailor
    -0.06
    .fs
    -0.06
    reated
    -0.06
     Snow
    -0.06
    emma
    -0.06
    ardo
    -0.06
    borg
    -0.06
    quier
    -0.05
    imals
    -0.05
    POSITIVE LOGITS
     fishing
    0.10
     fishermen
    0.09
     Fishing
    0.08
     fish
    0.08
    /channel
    0.07
    ICAST
    0.07
     tuna
    0.07
     rigs
    0.07
    _CAST
    0.07
    æįķ
    0.07
    Activations Density 0.029%

    No Known Activations