© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29697
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically periods

    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
    iate
    -0.06
     McKenzie
    -0.06
     Mart
    -0.06
    _FLUSH
    -0.05
    ÅĻeh
    -0.05
     hol
    -0.05
    ammo
    -0.05
    Ñģм
    -0.05
     congr
    -0.05
    .getNumber
    -0.05
    POSITIVE LOGITS
     ActiveForm
    0.10
    ancybox
    0.08
    isphere
    0.08
    uitka
    0.07
    FirstChild
    0.07
    stdexcept
    0.07
     EXEMPLARY
    0.07
    iesel
    0.07
    æĺł
    0.07
    ACLE
    0.07
    Activations Density 0.000%

    No Known Activations