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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 75981
    Prev
    Next
    INDEX
    Explanations

    questions and discussions about uncertainty or speculation

    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
    tera
    -0.07
     noqa
    -0.06
    utura
    -0.06
    ÏĦή
    -0.06
     Pods
    -0.06
     Fach
    -0.06
    ogne
    -0.06
    iag
    -0.06
     dbl
    -0.06
    æ·
    -0.05
    POSITIVE LOGITS
     talks
    0.09
     possibility
    0.08
     plan
    0.08
     plans
    0.08
     talk
    0.07
     talked
    0.07
    project
    0.07
     project
    0.07
    plan
    0.07
    iquid
    0.07
    Activations Density 0.054%

    No Known Activations