© 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. 116820
    Prev
    Next
    INDEX
    Explanations

    dates and years related to events or occurrences

    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
    âĢ¦↵
    -0.07
    nar
    -0.06
    783
    -0.06
     lands
    -0.06
     Bau
    -0.06
    923
    -0.06
     insiders
    -0.06
    dou
    -0.06
     cart
    -0.05
     âĢ¦↵
    -0.05
    POSITIVE LOGITS
    åŃĺæ¡£
    0.09
    (=)
    0.07
    licos
    0.07
    .rt
    0.07
    mpp
    0.07
    åµ
    0.07
    foundation
    0.07
     تض
    0.07
    ëł
    0.07
    $MESS
    0.07
    Activations Density 0.005%

    No Known Activations