© 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. 18185
    Prev
    Next
    INDEX
    Explanations

    quotes about personal experiences and insights regarding sexuality

    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
     ↵
    -0.07
    #:
    -0.06
     folks
    -0.06
    -0.06
    OC
    -0.06
    APPER
    -0.06
    rof
    -0.05
     likely
    -0.05
    202
    -0.05
    coni
    -0.05
    POSITIVE LOGITS
    -sdk
    0.07
    -thumb
    0.07
    _mex
    0.07
    ovny
    0.07
    avn
    0.07
    pcm
    0.07
    :System
    0.07
    azor
    0.07
    alus
    0.07
    PRS
    0.07
    Activations Density 0.018%

    No Known Activations