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

    Neuronpedia

    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. 118146
    Prev
    Next
    INDEX
    Explanations

    references to changes and modifications 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
    rose
    -0.08
    isku
    -0.07
    µľ
    -0.07
    udge
    -0.07
    geh
    -0.07
    /Library
    -0.07
    ridor
    -0.06
    é§
    -0.06
    ONO
    -0.06
    ÏĢοÏį
    -0.06
    POSITIVE LOGITS
    Made
    0.10
     made
    0.10
     Made
    0.09
    made
    0.09
    /add
    0.09
    /Add
    0.08
    ìĤ¬íķŃ
    0.08
     MADE
    0.08
    -made
    0.07
     permanent
    0.07
    Activations Density 0.050%

    No Known Activations