© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 61656
    Prev
    Next
    INDEX
    Explanations

    references to economic grants and funding in a corporate context

    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
    IFn
    -0.07
    ysa
    -0.07
    _mE
    -0.07
    ÌĢ
    -0.07
    /null
    -0.07
    emoc
    -0.07
    _mD
    -0.07
    _tC
    -0.07
    uben
    -0.07
    _mC
    -0.07
    POSITIVE LOGITS
     Cron
    0.06
    zych
    0.06
     hyp
    0.06
    odule
    0.06
    aya
    0.06
     plant
    0.06
    ź
    0.06
    elage
    0.06
     recipient
    0.06
     Manufacturing
    0.06
    Activations Density 0.001%

    No Known Activations