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. 96110
    Prev
    Next
    INDEX
    Explanations

    technical terms related to procedures and modifications in systems

    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
    ame
    -0.08
    YG
    -0.07
    esium
    -0.07
    511
    -0.06
    enties
    -0.06
    enso
    -0.06
    aktu
    -0.06
    516
    -0.06
    hd
    -0.06
    idth
    -0.06
    POSITIVE LOGITS
    tz
    0.08
    æ¯
    0.06
    Ø·ÙĨ
    0.06
     far
    0.06
    .console
    0.06
     cob
    0.06
    ãģĵãģ¡ãĤī
    0.06
    .normalized
    0.06
     bidi
    0.06
    edir
    0.06
    Activations Density 0.054%

    No Known Activations