Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3618
    Prev
    Next
    INDEX
    Explanations

    temporal phrases related to weeks and months

    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
    458
    -0.07
    .setParent
    -0.06
     Kurd
    -0.06
    _VF
    -0.06
    (predicate
    -0.06
    Ø´ÙĪØ±
    -0.06
    [frame
    -0.06
    ais
    -0.06
    ourg
    -0.06
    ãĥ«ãĥķ
    -0.06
    POSITIVE LOGITS
     ago
    0.09
    erli
    0.08
    ghi
    0.07
    YPES
    0.07
    cono
    0.07
    cco
    0.07
     spent
    0.07
    udic
    0.07
    kaar
    0.07
     назад
    0.06
    Activations Density 0.063%

    No Known Activations