© 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. 57205
    Prev
    Next
    INDEX
    Explanations

    instances of sharing or exchanging information and ideas

    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
    occo
    -0.08
    amd
    -0.07
    umd
    -0.07
    abox
    -0.07
    iks
    -0.06
    ked
    -0.06
     neger
    -0.06
    ddit
    -0.06
    relationships
    -0.06
    .managed
    -0.06
    POSITIVE LOGITS
    /share
    0.10
     resources
    0.10
     expertise
    0.09
     information
    0.09
     experience
    0.08
     knowledge
    0.08
     ideas
    0.08
    å½¼
    0.07
    resources
    0.07
     share
    0.07
    Activations Density 0.014%

    No Known Activations