© 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. 59121
    Prev
    Next
    INDEX
    Explanations

    elements related to the structure and functionality of speakerphone technology

    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
    ngen
    -0.06
    nic
    -0.06
     sam
    -0.06
    loit
    -0.06
    ÑĤоÑĩ
    -0.06
    awe
    -0.06
     sm
    -0.06
    umes
    -0.06
     Broadway
    -0.06
    Broad
    -0.06
    POSITIVE LOGITS
    inka
    0.07
    acon
    0.07
    .annot
    0.07
     surface
    0.07
     Surface
    0.07
     αÏĨ
    0.06
    _delegate
    0.06
    ormsg
    0.06
    paged
    0.06
    otionEvent
    0.06
    Activations Density 0.004%

    No Known Activations