© 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. 9-LLAMASCOPE-RES-131K
    11. 98058
    Prev
    Next
    INDEX
    Explanations

    paragraphs with the letter "L" at the start

    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
    å°½
    -0.07
    WB
    -0.07
     Gree
    -0.07
    ngör
    -0.06
    QUAL
    -0.06
     BB
    -0.06
    frag
    -0.06
    _WORLD
    -0.06
    äll
    -0.06
    862
    -0.06
    POSITIVE LOGITS
    506
    0.07
    QRS
    0.07
    ogui
    0.06
    etin
    0.06
    urette
    0.06
    esso
    0.06
     un
    0.06
    reds
    0.06
    enin
    0.06
     Nad
    0.06
    Activations Density 0.709%

    No Known Activations