© 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. 17-LLAMASCOPE-RES-131K
    11. 129230
    Prev
    Next
    INDEX
    Explanations

    terms related to wallpaper and decorative wall elements

    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
    chet
    -0.07
    té
    -0.07
    amework
    -0.07
    appy
    -0.07
    еÑģÑĮ
    -0.07
    oggler
    -0.07
    wit
    -0.07
    ewear
    -0.06
    OfWork
    -0.06
    /start
    -0.06
    POSITIVE LOGITS
    ing
    0.09
    ed
    0.08
    arus
    0.07
    edn
    0.07
    edReader
    0.07
    ined
    0.07
    å¼µ
    0.07
    hythm
    0.06
    inge
    0.06
    ius
    0.06
    Activations Density 0.002%

    No Known Activations