© 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. 17-LLAMASCOPE-RES-131K
    11. 39523
    Prev
    Next
    INDEX
    Explanations

    sentences that contain advice or guidance

    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
    aar
    -0.08
    ìĿ´ìĸ´
    -0.07
    ritten
    -0.07
    anja
    -0.07
    ách
    -0.07
    enko
    -0.07
    OVE
    -0.07
    ORIA
    -0.06
    reta
    -0.06
    elow
    -0.06
    POSITIVE LOGITS
    ino
    0.07
     try
    0.07
    thal
    0.07
     ÑģÑĤа
    0.07
     Try
    0.06
     Studies
    0.06
    Studies
    0.06
    Falsy
    0.06
    Try
    0.06
    -urlencoded
    0.06
    Activations Density 0.013%

    No Known Activations