© 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. 58869
    Prev
    Next
    INDEX
    Explanations

    connections or transitions between disparate elements

    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
    utherford
    -0.07
    ascal
    -0.07
    acades
    -0.07
    reon
    -0.07
    atica
    -0.07
    alytics
    -0.07
    atus
    -0.07
     Bout
    -0.07
    .free
    -0.07
     pione
    -0.06
    POSITIVE LOGITS
     unlike
    0.07
    omite
    0.06
    abr
    0.06
    erm
    0.06
     nar
    0.06
    omi
    0.06
     differently
    0.05
     iron
    0.05
     DISCLAIM
    0.05
     Willis
    0.05
    Activations Density 0.026%

    No Known Activations