© 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. 56118
    Prev
    Next
    INDEX
    Explanations

    references to specific dates, times, or events related to announcements

    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
    ³
    -0.07
    ษ
    -0.07
     tub
    -0.06
    ardon
    -0.06
    748
    -0.06
    anic
    -0.06
    ìĸij
    -0.06
    tae
    -0.06
    .sol
    -0.06
    uish
    -0.06
    POSITIVE LOGITS
     actual
    0.15
     actually
    0.14
    actual
    0.14
     Actual
    0.13
    Actual
    0.13
    _actual
    0.12
     indeed
    0.12
    actually
    0.12
    å®ŀéĻħ
    0.11
     ìĭ¤ìłľ
    0.10
    Activations Density 0.104%

    No Known Activations