© 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. 15-LLAMASCOPE-RES-131K
    11. 88709
    Prev
    Next
    INDEX
    Explanations

    significant numerical data or statistics

    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
    esse
    -0.09
     å¯Į
    -0.07
    orth
    -0.07
    iez
    -0.07
    iya
    -0.07
    ÑĥÑĪ
    -0.07
    _interrupt
    -0.07
    orque
    -0.06
    oth
    -0.06
    klad
    -0.06
    POSITIVE LOGITS
    ria
    0.06
     https
    0.06
    https
    0.06
     edition
    0.06
    Ø¡
    0.06
    Cons
    0.06
    eldon
    0.06
    cons
    0.06
     cons
    0.05
     Cons
    0.05
    Activations Density 0.058%

    No Known Activations