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. 44301
    Prev
    Next
    INDEX
    Explanations

    references to the name "Todd."

    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
    izmet
    -0.07
    ezi
    -0.07
    egend
    -0.07
    Enlarge
    -0.07
    ivor
    -0.06
    auss
    -0.06
    ease
    -0.06
    e
    -0.06
    rupa
    -0.06
    oth
    -0.06
    POSITIVE LOGITS
    ler
    0.17
    ington
    0.10
    ling
    0.09
    hunter
    0.09
    zilla
    0.09
    LER
    0.09
    lers
    0.08
    les
    0.08
     Gur
    0.08
    ays
    0.08
    Activations Density 0.002%

    No Known Activations