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. 44339
    Prev
    Next
    INDEX
    Explanations

    special characters and foreign language terms

    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
    аж
    -0.06
    ires
    -0.06
    ária
    -0.06
    chte
    -0.05
    ARI
    -0.05
    ÂĬ
    -0.05
    iki
    -0.05
    atura
    -0.05
    Vect
    -0.05
     Gins
    -0.05
    POSITIVE LOGITS
    ey
    0.16
    eyed
    0.15
    eye
    0.11
    ged
    0.10
    eyse
    0.09
    -double
    0.09
    ей
    0.09
     double
    0.09
    EY
    0.09
    gie
    0.09
    Activations Density 0.002%

    No Known Activations