© 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. 93000
    Prev
    Next
    INDEX
    Explanations

    capitalization patterns, particularly the use of the word "OW"

    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
    undry
    -0.08
    nova
    -0.07
    ovel
    -0.07
    ichten
    -0.07
    sis
    -0.07
    er
    -0.07
    oÅĪ
    -0.07
    erro
    -0.07
    iversit
    -0.07
    kelig
    -0.07
    POSITIVE LOGITS
    icz
    0.08
    ei
    0.08
    adia
    0.07
    czy
    0.07
    ls
    0.07
    rad
    0.07
    dh
    0.06
    atty
    0.06
    yer
    0.06
    els
    0.06
    Activations Density 0.023%

    No Known Activations