© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 105645
    Prev
    Next
    INDEX
    Explanations

    negative assertions or statements of refusal

    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
    ikel
    -0.07
    amber
    -0.07
    elman
    -0.06
    oog
    -0.06
    agos
    -0.06
    éric
    -0.06
     Integral
    -0.06
    osu
    -0.06
    _Clear
    -0.06
    _pg
    -0.06
    POSITIVE LOGITS
     conventional
    0.08
     conform
    0.07
    .Exception
    0.06
     convention
    0.06
     clutter
    0.06
     use
    0.06
     touching
    0.06
     conforms
    0.06
    744
    0.06
     ash
    0.06
    Activations Density 0.044%

    No Known Activations