© 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. 78052
    Prev
    Next
    INDEX
    Explanations

    references to figures, tables, and data from research or academic 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
    orough
    -0.06
     Manus
    -0.06
    tz
    -0.06
    ÏģοÏį
    -0.05
     axiom
    -0.05
     afford
    -0.05
    onym
    -0.05
     dem
    -0.05
    str
    -0.05
     dam
    -0.05
    POSITIVE LOGITS
     adapted
    0.18
    adapt
    0.16
     courtesy
    0.16
     Adapt
    0.16
    taken
    0.15
    (Source
    0.14
     source
    0.13
     taken
    0.13
     Source
    0.13
     adaptation
    0.13
    Activations Density 0.246%

    No Known Activations