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

    Neuronpedia

    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. 41263
    Prev
    Next
    INDEX
    Explanations

    calls to cease harmful or unwanted 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
    arya
    -0.06
    agina
    -0.06
    utschein
    -0.06
    olds
    -0.06
    -archive
    -0.06
    ricks
    -0.06
    yonel
    -0.06
    imates
    -0.06
    athom
    -0.05
    abler
    -0.05
    POSITIVE LOGITS
     Vulcan
    0.06
    niž
    0.06
    à¥įरय
    0.06
    csi
    0.06
    aken
    0.06
    otu
    0.06
     being
    0.06
    ertime
    0.06
    _feed
    0.06
     TCHAR
    0.06
    Activations Density 0.010%

    No Known Activations