© 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. 72943
    Prev
    Next
    INDEX
    Explanations

    contractions and possessive forms in text

    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
     although
    -0.07
    aux
    -0.06
     ki
    -0.06
     ke
    -0.05
    2
    -0.05
    oun
    -0.05
    ering
    -0.05
     coordinating
    -0.05
    -0.05
    of
    -0.05
    POSITIVE LOGITS
    nock
    0.09
    lers
    0.08
    iets
    0.08
    ÏģÏĮ
    0.08
    TERS
    0.07
    ufs
    0.07
    tors
    0.07
    wart
    0.07
    å¦
    0.07
    Ð¤ÐĽ
    0.07
    Activations Density 0.021%

    No Known Activations