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. 5473
    Prev
    Next
    INDEX
    Explanations

    instances of a specific noun or proper noun

    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
    s
    -0.10
    sav
    -0.07
    are
    -0.06
    ork
    -0.06
    139
    -0.06
    124
    -0.06
    ild
    -0.06
    ales
    -0.06
     Hipp
    -0.06
    ale
    -0.06
    POSITIVE LOGITS
    ewart
    0.09
    esson
    0.08
    urette
    0.08
    linger
    0.07
    ãĥ¼ãĥ¬
    0.07
    avo
    0.07
    alach
    0.07
    isoner
    0.07
    mise
    0.07
    ifer
    0.07
    Activations Density 0.003%

    No Known Activations