Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 11531
    Prev
    Next
    INDEX
    Explanations

    places and notable geographic features

    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
    zyst
    -0.08
    .catalog
    -0.07
    acak
    -0.07
    MBProgressHUD
    -0.07
    ytt
    -0.07
    buah
    -0.07
     JACK
    -0.07
    udas
    -0.07
    Ïĩα
    -0.06
    ãģĭãģĹ
    -0.06
    POSITIVE LOGITS
     Peak
    0.14
     peak
    0.11
    Peak
    0.11
     peaks
    0.09
    peak
    0.09
     Peaks
    0.09
     Pike
    0.09
    _peak
    0.08
     peaked
    0.08
    /Peak
    0.07
    Activations Density 0.002%

    No Known Activations