© 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 EvalsExportsinterp-engineNEWAPI 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. 117971
    Prev
    Next
    INDEX
    Explanations

    statements related to logical conditions and predicates in programming

    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
     pari
    -0.07
    STRUCTOR
    -0.07
    Æł
    -0.07
    óż
    -0.06
    TOCOL
    -0.06
    -fontawesome
    -0.06
    uncated
    -0.06
    .called
    -0.06
    celik
    -0.06
    .vel
    -0.06
    POSITIVE LOGITS
     Boolean
    0.09
     falsehood
    0.08
     truth
    0.08
     false
    0.08
    .bool
    0.08
     conditions
    0.08
     Truth
    0.07
     Bool
    0.07
     logic
    0.07
     untrue
    0.07
    Activations Density 0.076%

    No Known Activations