© 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. 81294
    Prev
    Next
    INDEX
    Explanations

    references to supernatural phenomena and their characteristics

    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
    ardon
    -0.07
    ñana
    -0.07
    _MAY
    -0.07
    ÙĪزÛĮ
    -0.07
    rypton
    -0.07
    .FLAG
    -0.07
     cÆ°
    -0.07
     æĬķ稿æĹ¥
    -0.07
    urma
    -0.07
    vez
    -0.07
    POSITIVE LOGITS
    959
    0.07
    543
    0.06
    oom
    0.06
     junk
    0.06
    avirus
    0.06
     Seen
    0.05
     Ka
    0.05
    988
    0.05
     Kot
    0.05
     observable
    0.05
    Activations Density 0.001%

    No Known Activations