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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 1489
    Prev
    Next
    INDEX
    Explanations

    quantitative expressions indicating quantities or measurements exceeding certain values

    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
    rox
    -0.07
    inalg
    -0.07
    luet
    -0.07
    cosity
    -0.07
    roz
    -0.06
    опаÑģ
    -0.06
    elib
    -0.06
     Lage
    -0.06
     пÑĥ
    -0.06
    οÏįν
    -0.06
    POSITIVE LOGITS
    900
    0.07
     Kurul
    0.07
     dozen
    0.07
    Collapse
    0.06
    0.06
    400
    0.06
    700
    0.06
    å¾Ģ
    0.06
    ä¹İ
    0.06
    autical
    0.06
    Activations Density 0.018%

    No Known Activations