© 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. 54544
    Prev
    Next
    INDEX
    Explanations

    references to specific characters or elements from literary works

    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
    .ld
    -0.07
     плаÑģÑĤи
    -0.07
    .libs
    -0.07
    lacak
    -0.07
     pena
    -0.07
    .communic
    -0.06
     erotico
    -0.06
    lements
    -0.06
    erdale
    -0.06
    çīĩ
    -0.06
    POSITIVE LOGITS
    ummings
    0.07
    ungi
    0.06
    .spark
    0.06
    çĻ»åł´
    0.05
    aged
    0.05
    unset
    0.05
    icker
    0.05
    bucket
    0.05
     fo
    0.05
     island
    0.05
    Activations Density 0.005%

    No Known Activations