© 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. 83650
    Prev
    Next
    INDEX
    Explanations

    contradictory statements and nuanced expressions

    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
    afen
    -0.07
    imum
    -0.06
    ount
    -0.05
    acula
    -0.05
    nton
    -0.05
    IMUM
    -0.05
    une
    -0.05
     bac
    -0.05
    bum
    -0.05
     qu
    -0.05
    POSITIVE LOGITS
    icari
    0.08
    ysa
    0.08
    ippers
    0.07
    bris
    0.07
    assin
    0.07
    bens
    0.07
    ÑĮого
    0.07
    ewan
    0.07
     verg
    0.07
    chai
    0.07
    Activations Density 0.081%

    No Known Activations