© 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. 87489
    Prev
    Next
    INDEX
    Explanations

    financial performance indicators and projections related to a company's earnings

    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
    ousel
    -0.07
     fore
    -0.07
    Mana
    -0.07
    ìķħ
    -0.06
    ÂŃt
    -0.06
    .digital
    -0.06
    -stats
    -0.06
    éŁ¿
    -0.06
    egrity
    -0.06
    unya
    -0.06
    POSITIVE LOGITS
     Heck
    0.06
    ãĥ³ãĤ¹
    0.06
    же
    0.06
     Whisper
    0.06
    urry
    0.06
    lies
    0.06
     Saunders
    0.06
     Yun
    0.06
    amo
    0.06
     Sands
    0.06
    Activations Density 0.002%

    No Known Activations