© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 61861
    Prev
    Next
    INDEX
    Explanations

    numbers and sequences related to lists or rankings

    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
    pez
    -0.07
     zav
    -0.06
    Matchers
    -0.06
    κα
    -0.06
    uchs
    -0.06
    phas
    -0.06
    uhe
    -0.06
    elves
    -0.06
    pheres
    -0.06
     Animalia
    -0.06
    POSITIVE LOGITS
     reasons
    0.09
     ways
    0.08
     reason
    0.07
    pom
    0.06
    åİŁåĽł
    0.06
    ebek
    0.06
    gress
    0.06
     Deb
    0.06
     hone
    0.06
     why
    0.06
    Activations Density 0.018%

    No Known Activations