© 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. 85787
    Prev
    Next
    INDEX
    Explanations

    elements related to updates and revisions 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
    ÏĦÏĥ
    -0.06
     restored
    -0.06
    iem
    -0.06
    森
    -0.06
    871
    -0.06
    acher
    -0.06
    мена
    -0.05
    ctl
    -0.05
    .ejb
    -0.05
    oni
    -0.05
    POSITIVE LOGITS
     grow
    0.11
    ä¸įæĸŃ
    0.10
     grows
    0.10
    Grow
    0.10
     Grow
    0.09
    grow
    0.09
    .mutable
    0.09
    .update
    0.09
    -update
    0.09
     update
    0.09
    Activations Density 0.095%

    No Known Activations