© 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. 119473
    Prev
    Next
    INDEX
    Explanations

    attributes and values related to user interface or graphic properties

    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
    539
    -0.07
    1
    -0.06
    879
    -0.06
    917
    -0.06
    91
    -0.06
    658
    -0.06
    907
    -0.06
    713
    -0.06
     floats
    -0.06
     object
    -0.05
    POSITIVE LOGITS
    Disposition
    0.07
    /tty
    0.07
     ADVISED
    0.07
    ocks
    0.07
    idual
    0.07
    anela
    0.07
    autoplay
    0.07
    hape
    0.06
    raquo
    0.06
    ระ
    0.06
    Activations Density 0.007%

    No Known Activations