© 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. 60598
    Prev
    Next
    INDEX
    Explanations

    titles and headings in a structured text

    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
    CanBe
    -0.06
    //(
    -0.06
     Schwe
    -0.06
     Schro
    -0.06
    èĭĹ
    -0.06
     jih
    -0.06
    _closure
    -0.06
     peÄį
    -0.06
     soru
    -0.06
    ãģĹãĤĩ
    -0.06
    POSITIVE LOGITS
     how
    0.09
    ding
    0.08
     why
    0.08
     reflections
    0.08
    ugen
    0.07
    loub
    0.07
    tm
    0.07
    how
    0.06
    ipers
    0.06
    endum
    0.06
    Activations Density 0.026%

    No Known Activations