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

    Neuronpedia

    Jacobian LensNEW
    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. 88778
    Prev
    Next
    INDEX
    Explanations

    complex interactions and causal relationships in various 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
    iants
    -0.08
    LLU
    -0.07
    utomation
    -0.07
    ÏĦÏīν
    -0.07
    stantiate
    -0.07
    stroy
    -0.07
    uta
    -0.07
    ÑĥÑĢн
    -0.07
    .Transactional
    -0.07
    LBL
    -0.07
    POSITIVE LOGITS
     neler
    0.07
     few
    0.07
     include
    0.07
    :↵
    0.06
    :
    0.06
     Cop
    0.06
     varied
    0.06
     premises
    0.06
     manifold
    0.06
    both
    0.06
    Activations Density 0.045%

    No Known Activations