© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 118336
    Prev
    Next
    INDEX
    Explanations

    accounting and record-keeping terminology

    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
    ÙĤÛĮ
    -0.07
    TRL
    -0.07
    itom
    -0.07
    Indented
    -0.06
     kancel
    -0.06
    entiful
    -0.06
    สà¸Ķ
    -0.06
    AZY
    -0.06
    à¸ĵà¸ij
    -0.06
    ãĥ¼ãĥ«ãĥī
    -0.06
    POSITIVE LOGITS
    idar
    0.06
    orny
    0.06
    irts
    0.06
    uben
    0.06
    ully
    0.05
    642
    0.05
    Connect
    0.05
    ÏĥÏĥ
    0.05
    oden
    0.05
    ucky
    0.05
    Activations Density 0.000%

    No Known Activations