© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 28940
    Prev
    Next
    INDEX
    Explanations

    references to responsible practices in resource development

    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
    uze
    -0.07
    usz
    -0.07
     post
    -0.07
    HAV
    -0.07
    ogl
    -0.06
    allee
    -0.06
     only
    -0.06
    contra
    -0.06
     conc
    -0.06
    LOY
    -0.06
    POSITIVE LOGITS
     yourselves
    0.08
    mares
    0.07
    è½
    0.07
     ourselves
    0.06
     scientific
    0.06
    ector
    0.06
    our
    0.06
     kå
    0.06
    shelf
    0.06
    ezier
    0.06
    Activations Density 0.000%

    No Known Activations