© 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. 15-LLAMASCOPE-RES-131K
    11. 547
    Prev
    Next
    INDEX
    Explanations

    statements related to strategies or recommendations for improvement

    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
    Ấ
    -0.08
    930
    -0.07
    Enlarge
    -0.07
    anta
    -0.07
    WL
    -0.07
    xdb
    -0.06
    itch
    -0.06
    anton
    -0.06
    atten
    -0.06
    .vm
    -0.06
    POSITIVE LOGITS
     via
    0.07
    via
    0.07
    457
    0.06
    ÑģÑĭ
    0.06
    365
    0.06
    ville
    0.06
    UTOR
    0.06
    odal
    0.06
    ynchronously
    0.06
    olson
    0.06
    Activations Density 0.010%

    No Known Activations