© 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. 90399
    Prev
    Next
    INDEX
    Explanations

    references to specific organizations and their products or offerings

    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
    uries
    -0.07
    euillez
    -0.06
    áz
    -0.06
     Tie
    -0.06
    ей
    -0.06
    /cop
    -0.06
    ằng
    -0.06
    usher
    -0.06
     mec
    -0.06
    isations
    -0.06
    POSITIVE LOGITS
     list
    0.14
    list
    0.10
    .list
    0.09
     roster
    0.09
     List
    0.08
    plist
    0.08
    _list
    0.08
     목ë¡Ŀ
    0.08
     lista
    0.08
    (list
    0.08
    Activations Density 0.062%

    No Known Activations