© 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 EvalsExportsAPI 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. 85531
    Prev
    Next
    INDEX
    Explanations

    editorial notes and annotations

    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
    ber
    -0.06
     ent
    -0.06
    obo
    -0.06
    am
    -0.06
    av
    -0.06
    atik
    -0.05
    vent
    -0.05
    at
    -0.05
    __
    -0.05
     stitches
    -0.05
    POSITIVE LOGITS
     note
    0.08
    eldorf
    0.08
    .scalablytyped
    0.07
    igel
    0.07
    ozÃŃ
    0.07
    ůr
    0.07
    ÑĤий
    0.07
    endl
    0.07
    uelles
    0.07
    è¨
    0.07
    Activations Density 0.004%

    No Known Activations