© 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. 72709
    Prev
    Next
    INDEX
    Explanations

    phrases related to user interaction and communication

    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
    rint
    -0.07
     double
    -0.06
    że
    -0.06
     ph
    -0.06
    ноÑģÑıÑĤ
    -0.06
    pit
    -0.06
    ripper
    -0.06
    gue
    -0.06
    ulur
    -0.06
    Ñıви
    -0.06
    POSITIVE LOGITS
     somehow
    0.15
     Somehow
    0.10
     somew
    0.10
     mechanism
    0.08
     somewhere
    0.08
     ways
    0.08
    å©·
    0.07
     mechanisms
    0.07
     Mechan
    0.07
     quelque
    0.07
    Activations Density 0.071%

    No Known Activations