© 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. 17-LLAMASCOPE-RES-131K
    11. 87640
    Prev
    Next
    INDEX
    Explanations

    financial information related to a specific company

    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
     èµ·
    -0.07
    weise
    -0.06
    ombok
    -0.06
     hos
    -0.05
    ãĤ§
    -0.05
     eg
    -0.05
    suit
    -0.05
     imp
    -0.05
    onna
    -0.05
    048
    -0.05
    POSITIVE LOGITS
    ãĤ¹ãĥĨãĤ£
    0.08
    zdy
    0.07
    èĤ¡
    0.07
    æݧ
    0.07
    _FF
    0.07
    igon
    0.07
    ewan
    0.07
     обÑĭ
    0.07
     âĹĦ
    0.07
    adows
    0.07
    Activations Density 0.003%

    No Known Activations