© 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. 86546
    Prev
    Next
    INDEX
    Explanations

    words that indicate the process of creation or causation

    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
    istring
    -0.08
    õi
    -0.08
    ancode
    -0.08
    ÐIJÑĢÑħÑĸв
    -0.08
     ayn
    -0.08
     _______,
    -0.08
    ãĤ¤ãĥ¤
    -0.08
    ittest
    -0.08
    Ñĸдно
    -0.08
    αÏģά
    -0.08
    POSITIVE LOGITS
    ly
    0.09
     thus
    0.09
     thereby
    0.09
     hence
    0.08
     therefore
    0.07
     this
    0.07
    thus
    0.07
     Thus
    0.07
    .
    0.07
    alto
    0.07
    Activations Density 0.043%

    No Known Activations