© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56988
    Prev
    Next
    INDEX
    Explanations

    mentions of academic titles, specifically "Professor" and related references

    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
    asonic
    -0.07
    orph
    -0.06
    gar
    -0.06
    breaking
    -0.06
    atoi
    -0.06
    ót
    -0.06
    omens
    -0.06
    tin
    -0.06
    ough
    -0.06
    aways
    -0.06
    POSITIVE LOGITS
    ial
    0.14
    ship
    0.11
     Emer
    0.09
    ession
    0.09
    ships
    0.09
    iate
    0.09
    IAL
    0.09
    hip
    0.08
    stown
    0.08
    à¥Ģय
    0.07
    Activations Density 0.020%

    No Known Activations