© 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. 119638
    Prev
    Next
    INDEX
    Explanations

    references to software components and tools

    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
    ustr
    -0.06
    Datum
    -0.06
     ph
    -0.06
    deque
    -0.06
    ember
    -0.06
     Johnston
    -0.06
    mere
    -0.05
    onom
    -0.05
    å°ļ
    -0.05
    VERSION
    -0.05
    POSITIVE LOGITS
    .rar
    0.09
    rar
    0.08
     rar
    0.07
    ZONE
    0.07
    شد
    0.07
     Region
    0.06
    rowsable
    0.06
    ÑĨвеÑĤ
    0.06
    nia
    0.06
     Ald
    0.06
    Activations Density 0.027%

    No Known Activations