© 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. 57366
    Prev
    Next
    INDEX
    Explanations

    temporal references and indicators of time

    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
    imei
    -0.07
    ilip
    -0.07
    egas
    -0.06
    bject
    -0.06
    illa
    -0.06
    acho
    -0.06
    éĢģæĸĻçĦ¡æĸĻ
    -0.06
    oph
    -0.06
    Æ°á»Łng
    -0.06
    ÙģØ´
    -0.06
    POSITIVE LOGITS
    obel
    0.08
    OffsetTable
    0.07
     ragaz
    0.07
     miêu
    0.07
    USTER
    0.07
    ãĥ¼ãĤ¯
    0.07
    HeaderCode
    0.06
    ÑģÑĤÑĢÑĥкÑĤоÑĢ
    0.06
    strup
    0.06
    libft
    0.06
    Activations Density 0.025%

    No Known Activations