© 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. 60936
    Prev
    Next
    INDEX
    Explanations

    mentions of time durations or years of experience

    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
    ÙĦÛĮت
    -0.07
    lient
    -0.06
    airy
    -0.06
    EMU
    -0.06
    ADED
    -0.06
    okane
    -0.06
    onga
    -0.06
    icits
    -0.06
    lict
    -0.06
     ><?
    -0.06
    POSITIVE LOGITS
     ago
    0.07
    as
    0.07
    edback
    0.06
    alm
    0.06
    .lon
    0.06
    ¹
    0.06
    ITLE
    0.06
    OTAL
    0.06
    ÑĤÑĶ
    0.06
    uspended
    0.06
    Activations Density 0.015%

    No Known Activations