© 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. 82079
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and descriptions of their environments

    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
    _intr
    -0.06
     bunk
    -0.06
    d
    -0.05
     pam
    -0.05
    all
    -0.05
     incom
    -0.05
    ovu
    -0.05
    gor
    -0.05
     Erg
    -0.05
    gro
    -0.05
    POSITIVE LOGITS
    ismet
    0.08
     street
    0.08
     двеÑĢ
    0.08
    rvé
    0.08
    _ENTER
    0.07
    Å¡ÃŃ
    0.07
     tiny
    0.07
    /licenses
    0.07
    zbollah
    0.07
     misleading
    0.07
    Activations Density 0.013%

    No Known Activations