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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 87700
    Prev
    Next
    INDEX
    Explanations

    sentence endings and punctuation marks

    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
    ange
    -0.07
    ag
    -0.07
    icle
    -0.07
    av
    -0.06
    ove
    -0.06
    ook
    -0.06
    :
    -0.06
    ol
    -0.06
    uck
    -0.06
    izz
    -0.06
    POSITIVE LOGITS
    redient
    0.07
     Additionally
    0.07
    Č↵
    0.07
    OptionPane
    0.07
     yyn
    0.07
    inflate
    0.07
    kili
    0.07
    .tie
    0.07
    ansi
    0.07
    /Peak
    0.07
    Activations Density 0.075%

    No Known Activations