© 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. 120432
    Prev
    Next
    INDEX
    Explanations

    statements about personal experiences and recommendations

    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
    isphere
    -0.07
    enberg
    -0.06
    etch
    -0.06
    enburg
    -0.06
    ONUS
    -0.06
    eria
    -0.06
    blem
    -0.06
    -opening
    -0.06
     Flood
    -0.06
    úng
    -0.06
    POSITIVE LOGITS
     FIRE
    0.08
     freedom
    0.08
     lifestyle
    0.08
    ziel
    0.07
    ivre
    0.07
    EXIT
    0.07
     Passive
    0.07
     passive
    0.07
     life
    0.07
     Freedom
    0.07
    Activations Density 0.005%

    No Known Activations