© 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. 28819
    Prev
    Next
    INDEX
    Explanations

    terms related to business operations and real estate listings

    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
    nants
    -0.07
     strstr
    -0.07
    ãģĤãĤĬãģĮãģ¨ãģĨ
    -0.06
    anut
    -0.06
    automatic
    -0.06
    .GetChild
    -0.06
    aic
    -0.06
    swire
    -0.06
    azole
    -0.06
    ungi
    -0.06
    POSITIVE LOGITS
    ovat
    0.06
    LAG
    0.06
    ova
    0.06
    iquement
    0.06
    lays
    0.06
    DF
    0.06
    igh
    0.06
     mouths
    0.06
     Ñģловами
    0.06
    127
    0.06
    Activations Density 0.068%

    No Known Activations