© 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. 5059
    Prev
    Next
    INDEX
    Explanations

    critical steps and processes in a discussion or narrative

    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
     General
    -0.06
    tü
    -0.06
    .opensource
    -0.06
    ãĥ¼ãĤ¹
    -0.06
    ecided
    -0.06
    assi
    -0.06
     Cata
    -0.06
     target
    -0.06
     Durch
    -0.06
    à¹ĥ
    -0.06
    POSITIVE LOGITS
    éĺ¶æ®µ
    0.08
     stage
    0.08
     part
    0.08
     phase
    0.08
     crucial
    0.08
    portion
    0.07
    Stage
    0.07
     portion
    0.07
    çİĦ
    0.07
    éĥ¨åĪĨ
    0.07
    Activations Density 0.052%

    No Known Activations