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. 43749
    Prev
    Next
    INDEX
    Explanations

    parenthetical expressions or references

    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
    ubl
    -0.07
    okus
    -0.06
    isco
    -0.06
    embro
    -0.06
     ëĭ¹ìĭľ
    -0.06
    让æĪij
    -0.06
    (origin
    -0.06
     vůbec
    -0.06
    ngr
    -0.06
    istor
    -0.06
    POSITIVE LOGITS
     if
    0.11
    unless
    0.11
    optional
    0.11
    if
    0.10
    please
    0.10
     unless
    0.10
    prefer
    0.10
     you
    0.10
     please
    0.10
     must
    0.10
    Activations Density 0.062%

    No Known Activations