© 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. 2113
    Prev
    Next
    INDEX
    Explanations

    punctuation marks indicating the end of sentences

    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
    s
    -0.09
    i
    -0.08
    n
    -0.07
    557
    -0.06
    es
    -0.06
     latter
    -0.06
    uar
    -0.06
    a
    -0.06
    v
    -0.06
     nearby
    -0.06
    POSITIVE LOGITS
    fillType
    0.08
    ystore
    0.08
    cctor
    0.08
     Redistributions
    0.08
    istrat
    0.08
    ERRU
    0.08
    inel
    0.08
    estroy
    0.07
    tep
    0.07
    unden
    0.07
    Activations Density 0.058%

    No Known Activations