© 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. 9-LLAMASCOPE-RES-131K
    11. 96753
    Prev
    Next
    INDEX
    Explanations

    discussions about various forms of loss or deficiency

    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
     ab
    -0.07
     Bradley
    -0.06
     Mens
    -0.06
    è¾Ľ
    -0.06
     Ab
    -0.06
    orean
    -0.06
    'gc
    -0.06
    ich
    -0.06
     eas
    -0.05
     IDictionary
    -0.05
    POSITIVE LOGITS
    Ñīи
    0.07
    ophil
    0.07
     Lump
    0.07
    缺
    0.07
    rypto
    0.07
    FFE
    0.06
    δε
    0.06
    ple
    0.06
    ami
    0.06
    MainThread
    0.06
    Activations Density 0.096%

    No Known Activations