© 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. 26893
    Prev
    Next
    INDEX
    Explanations

    words related to preparation or processes involving setup

    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
    itary
    -0.07
    jourd
    -0.06
    ỡ
    -0.06
    weed
    -0.06
    orus
    -0.06
    oggler
    -0.06
    ecz
    -0.06
     dealing
    -0.06
    iw
    -0.06
     clown
    -0.06
    POSITIVE LOGITS
     mie
    0.07
    ders
    0.07
    -lined
    0.06
     acompan
    0.06
    peech
    0.06
    .Apis
    0.06
     Noble
    0.06
     Beng
    0.06
    bian
    0.06
    новид
    0.06
    Activations Density 0.000%

    No Known Activations