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. 44239
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to a specific field or subject area

    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
    ystone
    -0.07
    ÙĨØ´
    -0.07
    wort
    -0.06
    кид
    -0.06
    /Area
    -0.06
    alent
    -0.06
    çĵľ
    -0.06
    pack
    -0.06
    kap
    -0.06
    genes
    -0.06
    POSITIVE LOGITS
    fter
    0.24
    fte
    0.12
    fer
    0.10
    FTER
    0.10
    nder
    0.09
    ft
    0.09
    ther
    0.09
    ften
    0.09
    fts
    0.08
    ferred
    0.08
    Activations Density 0.003%

    No Known Activations