© 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. 29850
    Prev
    Next
    INDEX
    Explanations

    elements relevant to product features and specifications

    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
    finity
    -0.07
    ence
    -0.06
    469
    -0.06
    tti
    -0.06
     wa
    -0.06
    arrow
    -0.06
     such
    -0.06
    asan
    -0.06
    alte
    -0.06
    leta
    -0.06
    POSITIVE LOGITS
    ODB
    0.07
    dur
    0.07
    Dur
    0.07
     durable
    0.07
     Dur
    0.07
     dur
    0.07
    ,strong
    0.07
     premium
    0.06
     proprietary
    0.06
     qualité
    0.06
    Activations Density 0.017%

    No Known Activations