© 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. 119604
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and their associated contexts in financial reports

    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
    ohl
    -0.07
    AMIL
    -0.07
    ledon
    -0.06
    /stdc
    -0.06
    uppy
    -0.06
     -:-
    -0.06
    _resolver
    -0.06
    ä¸ģ
    -0.06
    $class
    -0.06
    åĢĴ
    -0.06
    POSITIVE LOGITS
    izi
    0.07
    inos
    0.07
    окол
    0.07
    isis
    0.06
     period
    0.06
    cao
    0.06
     periodo
    0.06
    agu
    0.06
    bruar
    0.06
     Affero
    0.06
    Activations Density 0.003%

    No Known Activations