© 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. 26716
    Prev
    Next
    INDEX
    Explanations

    comments and references to error handling in a policy management context

    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
    egin
    -0.08
    onec
    -0.08
    leck
    -0.07
    売
    -0.07
    íĨłíĨł
    -0.07
    NullException
    -0.07
    zc
    -0.07
    ampoo
    -0.07
    _masks
    -0.07
    å¸Ń
    -0.07
    POSITIVE LOGITS
     test
    0.07
    NSS
    0.06
     case
    0.06
    test
    0.06
    Corner
    0.06
     Willi
    0.06
     cases
    0.05
     expected
    0.05
    omi
    0.05
     заÑħ
    0.05
    Activations Density 0.019%

    No Known Activations