© 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. 15-LLAMASCOPE-RES-131K
    11. 62362
    Prev
    Next
    INDEX
    Explanations

    occurrences of times and timings in the document

    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
    pars
    -0.10
    e
    -0.08
    oftware
    -0.08
    ÏĦεÏį
    -0.08
     latter
    -0.07
    IME
    -0.07
    a
    -0.07
    ãĥ³ãĤ¬
    -0.07
    ECTOR
    -0.07
    lated
    -0.07
    POSITIVE LOGITS
    adays
    0.08
    etheless
    0.07
    itre
    0.07
    bsites
    0.07
    ÑįÑĤомÑĥ
    0.07
    eters
    0.07
    @js
    0.07
    /pm
    0.06
    /post
    0.06
    rei
    0.06
    Activations Density 0.008%

    No Known Activations