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. 22-LLAMASCOPE-RES-131K
    6. 5668
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "of" and its variations

    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
    uen
    -0.07
    aller
    -0.06
    360
    -0.06
    reate
    -0.06
    ìĹ´
    -0.06
     rencont
    -0.05
    roid
    -0.05
    iÅŁ
    -0.05
     Schneider
    -0.05
    aise
    -0.05
    POSITIVE LOGITS
    ertas
    0.08
    åѤ
    0.07
    tember
    0.07
    ìĿ´ë²Ħ
    0.07
    isas
    0.07
    assis
    0.07
    Ñĩим
    0.07
    erta
    0.07
    icers
    0.07
    emoc
    0.07
    Activations Density 0.005%

    No Known Activations