Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 75014
    Prev
    Next
    INDEX
    Explanations

    specific names, places, or identifiers related to historical contexts

    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
    aurus
    -0.07
     Haskell
    -0.06
     ìļ°ë¦¬
    -0.06
     Pricing
    -0.06
    achten
    -0.06
     counselor
    -0.06
     ceremon
    -0.06
    enic
    -0.06
    zc
    -0.06
    .requests
    -0.06
    POSITIVE LOGITS
    ogo
    0.07
    Agents
    0.06
    182
    0.06
     Agents
    0.06
    897
    0.06
    ls
    0.06
    dist
    0.06
    )prepare
    0.06
    Executor
    0.06
    183
    0.06
    Activations Density 0.000%

    No Known Activations