© 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. 87172
    Prev
    Next
    INDEX
    Explanations

    descriptions of luxurious accommodations and their 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
    loor
    -0.08
     terminal
    -0.06
    //{{
    -0.06
    ÅĻÃŃ
    -0.06
     Terminal
    -0.06
    fout
    -0.06
     RSS
    -0.06
    .eval
    -0.06
    ivent
    -0.06
    prit
    -0.06
    POSITIVE LOGITS
    igne
    0.07
    oleon
    0.07
     Localization
    0.07
    apur
    0.06
    å¤ı
    0.06
    lij
    0.06
    æ¡IJ
    0.06
     Baba
    0.06
    ody
    0.06
     Village
    0.06
    Activations Density 0.008%

    No Known Activations