© 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. 2161
    Prev
    Next
    INDEX
    Explanations

    expressions of evaluation and criteria for approval or satisfaction

    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
    ÑĤал
    -0.07
    ALER
    -0.06
    ismet
    -0.06
    âĻ¡
    -0.06
     yem
    -0.06
    rahim
    -0.06
    ahi
    -0.06
    bucks
    -0.06
     kabil
    -0.06
    ìħĺ
    -0.06
    POSITIVE LOGITS
     satisfactory
    0.18
     satisfaction
    0.16
     Satisfaction
    0.15
     satisf
    0.15
     satisfied
    0.14
     acceptable
    0.14
     satisfy
    0.14
    atisf
    0.14
    acceptable
    0.12
     satisfies
    0.11
    Activations Density 0.028%

    No Known Activations