© 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. 126841
    Prev
    Next
    INDEX
    Explanations

    financial metrics and projections related to company operations and investments

    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
     Thumbnail
    -0.07
    pit
    -0.06
    alink
    -0.06
    _sta
    -0.06
    Thumbnail
    -0.06
    iyat
    -0.06
    STA
    -0.06
     Freedom
    -0.06
     impover
    -0.06
    łģ
    -0.05
    POSITIVE LOGITS
    apon
    0.07
    iode
    0.07
    iper
    0.07
    undry
    0.06
    oders
    0.06
     operations
    0.06
    agina
    0.06
    ivals
    0.06
     Kraj
    0.06
     project
    0.06
    Activations Density 0.005%

    No Known Activations