© 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. 30981
    Prev
    Next
    INDEX
    Explanations

    pronouns and words indicating a sense of service and reliability

    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
     Maur
    -0.06
    ym
    -0.06
     needs
    -0.06
    (s
    -0.06
    ↵
    -0.06
    Courtesy
    -0.05
    118
    -0.05
    elem
    -0.05
    wich
    -0.05
    ANI
    -0.05
    POSITIVE LOGITS
    nek
    0.08
     pride
    0.08
    763
    0.07
    nonnull
    0.07
    priv
    0.07
    rollo
    0.07
     lesb
    0.07
    /REC
    0.07
    (Handle
    0.07
     offer
    0.07
    Activations Density 0.026%

    No Known Activations