© 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. 93816
    Prev
    Next
    INDEX
    Explanations

    affirmative and future-oriented statements

    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
    oba
    -0.07
    sik
    -0.07
    ROUT
    -0.06
     komp
    -0.06
    Hope
    -0.06
    udu
    -0.06
    udem
    -0.06
    uta
    -0.06
    enou
    -0.06
    bio
    -0.06
    POSITIVE LOGITS
    utzer
    0.07
     excellent
    0.07
     excell
    0.07
     toe
    0.06
     soon
    0.06
     fare
    0.06
     '..',
    0.06
     great
    0.06
     success
    0.06
     equally
    0.06
    Activations Density 0.018%

    No Known Activations