© 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. 58762
    Prev
    Next
    INDEX
    Explanations

    significant elements related to structure and classification in various contexts

    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
    irsch
    -0.09
    iji
    -0.07
    ials
    -0.06
    org
    -0.06
    _dp
    -0.06
    amentos
    -0.06
    uman
    -0.06
    ulent
    -0.06
    ãģ¼
    -0.06
    uco
    -0.06
    POSITIVE LOGITS
    oret
    0.07
    ë¡ľëĬĶ
    0.07
     consist
    0.07
     consists
    0.07
     же
    0.07
     meanwhile
    0.07
     consisted
    0.06
    olars
    0.06
     ÑģоÑģÑĤоиÑĤ
    0.06
    ACHI
    0.06
    Activations Density 0.084%

    No Known Activations