© 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. 107657
    Prev
    Next
    INDEX
    Explanations

    concepts related to sensory perception and cognition interactions

    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
    plain
    -0.07
    egers
    -0.06
    prise
    -0.06
    ilon
    -0.06
     resort
    -0.06
    Ïĩι
    -0.06
    amu
    -0.06
     ÃĿ
    -0.06
     plain
    -0.06
     odv
    -0.06
    POSITIVE LOGITS
    iman
    0.07
    @Id
    0.06
    .ibatis
    0.06
    iye
    0.06
     looming
    0.06
    _utf
    0.06
    ħ§
    0.06
    icari
    0.06
    ib
    0.06
     flex
    0.06
    Activations Density 0.007%

    No Known Activations