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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 97816
    Prev
    Next
    INDEX
    Explanations

    terms related to physical sensations and respiratory actions

    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
    .readString
    -0.06
    osta
    -0.06
    eyed
    -0.06
     odds
    -0.06
    581
    -0.06
    ignment
    -0.06
     raw
    -0.06
    verity
    -0.06
    hti
    -0.05
     Bair
    -0.05
    POSITIVE LOGITS
    ableView
    0.08
     PropertyChangedEventArgs
    0.07
    аблиÑĨ
    0.07
     Enumerator
    0.07
    /ex
    0.07
    CPF
    0.06
    åŀ
    0.06
     breath
    0.06
    obbies
    0.06
    å§
    0.06
    Activations Density 0.007%

    No Known Activations