© 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. 42200
    Prev
    Next
    INDEX
    Explanations

    negative qualifiers related to comparisons and 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
    uchos
    -0.08
    vil
    -0.07
    ICODE
    -0.07
    à¹ģà¸ķ
    -0.07
     often
    -0.07
    DDevice
    -0.07
    å¢
    -0.07
    often
    -0.07
    unker
    -0.07
    ÅĻez
    -0.07
    POSITIVE LOGITS
     ever
    0.11
     except
    0.10
     anywhere
    0.09
     EVER
    0.09
     nÃło
    0.09
    except
    0.08
     any
    0.08
     anything
    0.07
     anymore
    0.07
     particularly
    0.07
    Activations Density 0.023%

    No Known Activations