© 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 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. 57299
    Prev
    Next
    INDEX
    Explanations

    phrases indicating progress or ongoing experiences

    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
    atre
    -0.07
    ovna
    -0.07
     Hughes
    -0.06
     Jarvis
    -0.06
    jer
    -0.06
    gs
    -0.06
    igs
    -0.06
    ationToken
    -0.06
    geme
    -0.06
     Heap
    -0.06
    POSITIVE LOGITS
    alama
    0.08
    -fw
    0.08
    illac
    0.07
    ebek
    0.07
    amam
    0.07
    ÑĢоиз
    0.07
     haven
    0.07
    okies
    0.07
     only
    0.07
    ноÑģ
    0.07
    Activations Density 0.005%

    No Known Activations