© 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. 5296
    Prev
    Next
    INDEX
    Explanations

    terms related to psychology and psychoactive practices

    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
    s
    -0.13
    sik
    -0.10
    ÏĤ
    -0.10
    sar
    -0.09
    sburg
    -0.09
    sak
    -0.09
    ioned
    -0.08
    ska
    -0.08
    wayne
    -0.08
     Surg
    -0.08
    POSITIVE LOGITS
    er
    0.07
    ette
    0.07
    ate
    0.06
    eur
    0.06
    old
    0.06
    ya
    0.06
    ever
    0.06
    iors
    0.06
    ther
    0.06
    etch
    0.06
    Activations Density 0.002%

    No Known Activations