© 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. 92538
    Prev
    Next
    INDEX
    Explanations

    themes related to artistic expression and the nature of existence

    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
    tero
    -0.07
    526
    -0.06
    abyrin
    -0.06
    EEK
    -0.06
    ifest
    -0.06
    aug
    -0.06
    aptop
    -0.06
    ound
    -0.06
     drum
    -0.06
    elps
    -0.06
    POSITIVE LOGITS
    ussen
    0.07
    pagesize
    0.06
     "~
    0.06
    _FR
    0.06
    ấ
    0.06
    bild
    0.06
    forder
    0.06
    'gc
    0.06
    ÙĦÙĦ
    0.06
    "urls
    0.06
    Activations Density 0.050%

    No Known Activations