© 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. 119994
    Prev
    Next
    INDEX
    Explanations

    instances of negation and assertions that challenge beliefs or assumptions

    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
    isch
    -0.07
    ãĥ¼ãĤ¸
    -0.07
    ìĸ¸
    -0.07
    ikh
    -0.07
    latable
    -0.07
    Ø·ÙĦ
    -0.06
    semb
    -0.06
    иÑĤелÑĮÑģÑĤва
    -0.06
    xon
    -0.06
     Mayer
    -0.06
    POSITIVE LOGITS
     true
    0.10
     happen
    0.09
     happening
    0.08
     happens
    0.08
    true
    0.08
     verdade
    0.07
    oti
    0.07
     happened
    0.07
     aconte
    0.07
     correct
    0.07
    Activations Density 0.017%

    No Known Activations