© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29061
    Prev
    Next
    INDEX
    Explanations

    references to bibliographic or citation-related terms

    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
    legates
    -0.06
    asar
    -0.06
     wound
    -0.06
    wat
    -0.06
    unker
    -0.05
    icular
    -0.05
    ugu
    -0.05
     mini
    -0.05
     known
    -0.05
    ÙĶ
    -0.05
    POSITIVE LOGITS
    Decoration
    0.08
    ัà¸į
    0.07
    avaÅŁ
    0.07
    .qq
    0.07
    .met
    0.07
    _GL
    0.07
    ÑĥÑģÑĤа
    0.07
    ternet
    0.07
    ëĶ
    0.07
    oor
    0.07
    Activations Density 0.003%

    No Known Activations