© 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. 15-LLAMASCOPE-RES-131K
    6. 26834
    Prev
    Next
    INDEX
    Explanations

    phrases that convey anticipation or the passage of time

    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
    oni
    -0.07
    595
    -0.06
    umbs
    -0.06
    oney
    -0.06
    zzle
    -0.06
    quette
    -0.06
    .twig
    -0.06
     perimeter
    -0.06
    /language
    -0.06
    DED
    -0.06
    POSITIVE LOGITS
    since
    0.08
    ä¹ħ
    0.07
    XHR
    0.07
     since
    0.07
     finally
    0.07
    _since
    0.06
    TINGS
    0.06
    zman
    0.06
    èĨ
    0.06
    çŃĨ
    0.06
    Activations Density 0.023%

    No Known Activations