© 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. 15-LLAMASCOPE-RES-131K
    11. 27397
    Prev
    Next
    INDEX
    Explanations

    features and specifications related to footwear or outdoor gear

    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
    ip
    -0.06
     or
    -0.06
     &
    -0.06
    .
    -0.06
    ut
    -0.06
    ux
    -0.06
    opp
    -0.06
     repent
    -0.05
    aka
    -0.05
    ls
    -0.05
    POSITIVE LOGITS
    ctrine
    0.08
    رÙĬس
    0.08
    vfs
    0.08
    ç´Ģ
    0.07
    itom
    0.07
    gom
    0.07
    ardown
    0.07
    /*č↵
    0.07
    ->__
    0.07
    _nh
    0.07
    Activations Density 0.005%

    No Known Activations