© 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. 71417
    Prev
    Next
    INDEX
    Explanations

    references to absence or errors in results or outputs

    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
    usu
    -0.07
    .googlecode
    -0.07
    ired
    -0.07
    chner
    -0.06
    .Reporting
    -0.06
    à¥įदर
    -0.06
    drv
    -0.06
    rella
    -0.06
    öh
    -0.06
    Ðħ
    -0.06
    POSITIVE LOGITS
     instead
    0.10
     вмеÑģÑĤ
    0.09
    /null
    0.09
    instead
    0.09
     Instead
    0.07
     rather
    0.07
     عÙĦÙĬÙĥ
    0.07
    /no
    0.06
     ë¹Ī
    0.06
    ElementException
    0.06
    Activations Density 0.015%

    No Known Activations