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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-LLAMASCOPE-RES-131K
    6. 96087
    Prev
    Next
    INDEX
    Explanations

    dialogues or conversational exchanges

    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
    æ¼
    -0.07
    oog
    -0.07
    ÑĢг
    -0.07
    oram
    -0.06
    adt
    -0.06
    aldo
    -0.06
    oloj
    -0.06
    unge
    -0.06
    iness
    -0.06
    ephir
    -0.06
    POSITIVE LOGITS
    /fw
    0.06
    AMPLE
    0.06
    å¾Ĵ
    0.06
    ë§¹
    0.05
     Venez
    0.05
    ded
    0.05
    éĢļçŁ¥
    0.05
    ÂĽ
    0.05
     Sizes
    0.05
     Pony
    0.05
    Activations Density 0.021%

    No Known Activations