© 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. 69565
    Prev
    Next
    INDEX
    Explanations

    evaluative phrases related to film quality and production status

    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
    938
    -0.07
    338
    -0.06
     perish
    -0.06
     pou
    -0.06
    andon
    -0.06
    avery
    -0.06
    andin
    -0.06
     hi
    -0.06
     Hog
    -0.05
    stp
    -0.05
    POSITIVE LOGITS
    RELEASE
    0.08
    _BUF
    0.08
    BUF
    0.08
    Tank
    0.07
    release
    0.07
     RELEASE
    0.07
    buster
    0.07
    ìĹ¼
    0.07
    ê°IJ
    0.07
    -release
    0.07
    Activations Density 0.001%

    No Known Activations