© 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. 127835
    Prev
    Next
    INDEX
    Explanations

    verbs that denote the act of removing, stopping, or disabling something

    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
    ÚĨار
    -0.08
     hữu
    -0.07
    rud
    -0.07
    _mD
    -0.07
    agrid
    -0.07
    (___
    -0.07
    undy
    -0.07
     takový
    -0.07
    _mC
    -0.07
     hala
    -0.07
    POSITIVE LOGITS
     traditional
    0.09
     boundaries
    0.08
     conventional
    0.08
     barriers
    0.08
     existing
    0.07
     inhib
    0.07
    traditional
    0.07
     previous
    0.07
     formal
    0.06
     inhibitors
    0.06
    Activations Density 0.062%

    No Known Activations