© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 2744
    Prev
    Next
    INDEX
    Explanations

    temporal indicators related to future events and deadlines

    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
    opp
    -0.08
    quila
    -0.07
    iaz
    -0.06
    stub
    -0.06
    stan
    -0.06
    omo
    -0.06
    леж
    -0.06
    .GetProperty
    -0.06
    abler
    -0.06
    umbn
    -0.06
    POSITIVE LOGITS
    ellido
    0.07
     coinc
    0.06
     Coin
    0.06
     Institutional
    0.06
    lasting
    0.06
    .runners
    0.06
    太éĥİ
    0.06
    [js
    0.06
    yt
    0.06
    eler
    0.06
    Activations Density 0.025%

    No Known Activations