© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 61660
    Prev
    Next
    INDEX
    Explanations

    documentation or comments in code

    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
     much
    -0.06
     Bos
    -0.06
     a
    -0.06
     till
    -0.06
    icens
    -0.06
    iza
    -0.06
    atre
    -0.06
     Mach
    -0.06
     (
    -0.06
    -0.06
    POSITIVE LOGITS
    rowsable
    0.09
    ByExample
    0.09
    μιÏĥ
    0.08
    uzey
    0.08
    .fx
    0.08
    .scalablytyped
    0.07
     INCIDENT
    0.07
    ëł
    0.07
     semiclass
    0.07
     INTERRUPTION
    0.07
    Activations Density 0.010%

    No Known Activations