© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 70497
    Prev
    Next
    INDEX
    Explanations

    indicators of emotional significance and personal connections

    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
    ubo
    -0.08
    ÐIJÑĢÑħÑĸв
    -0.07
    ever
    -0.07
    intl
    -0.07
    uhl
    -0.07
    ohana
    -0.07
    .every
    -0.07
    oftware
    -0.07
    ocker
    -0.07
    mostly
    -0.07
    POSITIVE LOGITS
     enough
    0.15
     apparently
    0.13
     Enough
    0.12
     sufficient
    0.10
     evidently
    0.10
     Apparently
    0.10
    Apparently
    0.09
     доÑģÑĤаÑĤ
    0.09
     sufficiently
    0.09
     presumably
    0.09
    Activations Density 0.113%

    No Known Activations