© 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. 70602
    Prev
    Next
    INDEX
    Explanations

    phrases expressing skepticism or doubt about societal norms and expectations

    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
    chl
    -0.07
    $MESS
    -0.07
    ãĥ¬ãĥ³
    -0.07
    Ñĵ
    -0.07
    ÏĥÏĢ
    -0.07
    ãĤ¾
    -0.06
    živ
    -0.06
    ulia
    -0.06
     povÄĽ
    -0.06
    emento
    -0.06
    POSITIVE LOGITS
     perfect
    0.15
    perfect
    0.12
     Perfect
    0.11
    Perfect
    0.11
     complete
    0.11
     perfection
    0.11
     completely
    0.10
     exact
    0.09
    å®Į
    0.09
     ideal
    0.09
    Activations Density 0.043%

    No Known Activations