© 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. 76372
    Prev
    Next
    INDEX
    Explanations

    references to neurons and their biological functions

    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
    _transition
    -0.06
    -inf
    -0.06
    itat
    -0.06
    cek
    -0.05
    imum
    -0.05
    obar
    -0.05
    tek
    -0.05
    iag
    -0.05
     vertical
    -0.05
     centre
    -0.05
    POSITIVE LOGITS
    axon
    0.08
    èĥŀ
    0.08
     CELL
    0.08
     posts
    0.08
    cell
    0.07
     cell
    0.07
    Posts
    0.07
    Reuse
    0.07
    _Cell
    0.07
     Posts
    0.07
    Activations Density 0.004%

    No Known Activations