© 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. 15-LLAMASCOPE-RES-131K
    11. 88799
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly in a list or roster format

    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
    Ā
    -0.07
    fov
    -0.07
    stor
    -0.07
    иÑĤеÑĤ
    -0.06
    utr
    -0.06
     legs
    -0.06
    net
    -0.06
    rien
    -0.06
    iceps
    -0.06
    ventory
    -0.06
    POSITIVE LOGITS
    Setter
    0.07
    -prefix
    0.06
    ãĥ¼ãĤ¹ãĥĪ
    0.06
     سبز
    0.06
    راÙĤ
    0.06
    à¥Ĥà¤ľ
    0.06
    osal
    0.06
     JAXBElement
    0.06
    ByVersion
    0.05
    341
    0.05
    Activations Density 0.022%

    No Known Activations