© 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. 79217
    Prev
    Next
    INDEX
    Explanations

    keywords related to algorithm parameters and their tuning processes

    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
    ERV
    -0.07
    NAV
    -0.07
    heim
    -0.07
    ière
    -0.07
    ObjectType
    -0.07
    holm
    -0.06
    ilip
    -0.06
    bum
    -0.06
     --------------------------------------------------------------------------↵
    -0.06
    enger
    -0.06
    POSITIVE LOGITS
     tuning
    0.07
     best
    0.07
     settings
    0.07
    SearchParams
    0.06
    ãĥģãĥ¥
    0.06
     optim
    0.06
    æľĢä½³
    0.06
     parameter
    0.06
     tune
    0.06
     parameters
    0.06
    Activations Density 0.057%

    No Known Activations