© 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 EvalsExportsAPI 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. 89002
    Prev
    Next
    INDEX
    Explanations

    contractions of the verb "to be" in different contexts

    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
    atre
    -0.08
    ogne
    -0.07
    zelf
    -0.07
    ãi
    -0.07
    icaret
    -0.07
    ร
    -0.07
    _OW
    -0.07
    quelle
    -0.07
    SizeMode
    -0.07
    âĢ¦"↵↵
    -0.07
    POSITIVE LOGITS
    tas
    0.08
    asc
    0.06
    orgen
    0.06
    rais
    0.06
    als
    0.06
     tun
    0.06
    ERE
    0.06
    duct
    0.06
    ere
    0.06
    ampo
    0.06
    Activations Density 0.068%

    No Known Activations