© 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. 17-LLAMASCOPE-RES-131K
    11. 107218
    Prev
    Next
    INDEX
    Explanations

    significant nouns and verbs in the context of comparisons or evaluations

    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
    ↵
    -0.07
    zn
    -0.07
    زار
    -0.06
     ört
    -0.06
     erotische
    -0.06
    å¸Ń
    -0.05
     nackte
    -0.05
    oÄŁ
    -0.05
    yx
    -0.05
    ÑħÑĥ
    -0.05
    POSITIVE LOGITS
    ButtonModule
    0.08
    contra
    0.07
    antity
    0.07
    istrovstvÃŃ
    0.07
    undry
    0.07
     miscellaneous
    0.07
     downright
    0.07
    .TryParse
    0.07
    porno
    0.07
    IconModule
    0.07
    Activations Density 0.001%

    No Known Activations