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. 43674
    Prev
    Next
    INDEX
    Explanations

    special characters, symbols, and non-standard text encoding

    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
    iqué
    -0.07
    onian
    -0.06
     fur
    -0.06
    rý
    -0.06
    ilden
    -0.06
     record
    -0.06
     Record
    -0.06
    ushima
    -0.06
    licative
    -0.06
    ream
    -0.06
    POSITIVE LOGITS
    hl
    0.12
    lr
    0.11
    safe
    0.11
    oq
    0.10
     hl
    0.10
    oe
    0.10
    tb
    0.09
    btn
    0.09
    sites
    0.09
    aq
    0.09
    Activations Density 0.004%

    No Known Activations