© 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. 116787
    Prev
    Next
    INDEX
    Explanations

    terms related to hypnosis and trance states

    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
    lier
    -0.08
    ело
    -0.07
    виÑħ
    -0.07
    à¥ĩà¤ľ
    -0.07
    line
    -0.07
     Äijỡ
    -0.06
    iser
    -0.06
    anel
    -0.06
    澤
    -0.06
    spir
    -0.06
    POSITIVE LOGITS
    amedi
    0.07
    ni
    0.07
     techniques
    0.07
    376
    0.07
    .googlecode
    0.06
    æķĪæŀľ
    0.06
    ebb
    0.06
    315
    0.06
     cracked
    0.06
    nio
    0.06
    Activations Density 0.002%

    No Known Activations