© 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. 79704
    Prev
    Next
    INDEX
    Explanations

    references to collaborative educational practices and writing communities

    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
    laus
    -0.07
    iam
    -0.07
    á»ĭ
    -0.06
    ensa
    -0.06
    orno
    -0.06
    idle
    -0.06
    jee
    -0.06
    ilis
    -0.06
     Military
    -0.06
    zos
    -0.06
    POSITIVE LOGITS
     scaffold
    0.07
    夫
    0.07
     å¹³æĸ¹
    0.07
     Teacher
    0.07
    äºĮ人
    0.07
    æĻ
    0.07
    (çģ«
    0.07
     veter
    0.07
     scaff
    0.06
    ï¼Īç¬ij
    0.06
    Activations Density 0.042%

    No Known Activations