© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 77565
    Prev
    Next
    INDEX
    Explanations

    negations and expressions indicating exceptions

    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
    amp
    -0.07
     Pessoa
    -0.06
    eba
    -0.06
     Pist
    -0.06
    umen
    -0.06
    dat
    -0.06
    ầu
    -0.06
    ater
    -0.06
     Genç
    -0.06
    нÑĥли
    -0.06
    POSITIVE LOGITS
     opin
    0.07
    hsi
    0.07
    avicon
    0.07
    ends
    0.06
    plusplus
    0.06
    LabelText
    0.06
    adget
    0.06
    ahi
    0.06
    AutoSize
    0.06
    ìļ
    0.06
    Activations Density 0.009%

    No Known Activations