© 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. 87797
    Prev
    Next
    INDEX
    Explanations

    references to corporate financial information and stock performance

    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
    fox
    -0.06
    aid
    -0.06
    ovic
    -0.06
    -
    -0.06
    _
    -0.06
     n
    -0.06
    eno
    -0.06
     Huff
    -0.06
    ally
    -0.06
     Wend
    -0.06
    POSITIVE LOGITS
    кав
    0.08
    DDS
    0.08
    stanov
    0.08
    ylko
    0.08
    adece
    0.08
    //{{
    0.08
    abase
    0.08
    ãĤīãģĹ
    0.08
    InParameter
    0.07
    orado
    0.07
    Activations Density 0.009%

    No Known Activations