© 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. 73198
    Prev
    Next
    INDEX
    Explanations

    occurrences of the past tense verb "had."

    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
     sometimes
    -0.07
     lately
    -0.07
    ynom
    -0.07
    jet
    -0.06
    gate
    -0.06
     Pett
    -0.06
    éľ
    -0.06
    "":
    -0.06
     recent
    -0.06
     Elo
    -0.06
    POSITIVE LOGITS
     Insecta
    0.07
    itus
    0.07
    Denied
    0.07
    ocos
    0.06
    ónico
    0.06
    )((((
    0.06
    icum
    0.06
    ики
    0.06
    EMY
    0.06
     Primer
    0.06
    Activations Density 0.000%

    No Known Activations