© 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. 76497
    Prev
    Next
    INDEX
    Explanations

    concepts related to personal attributes or characteristics

    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
    ither
    -0.06
     terrible
    -0.06
    zd
    -0.06
    oney
    -0.06
    ala
    -0.06
    LEX
    -0.06
     several
    -0.06
    âĢĤ
    -0.06
     Jennings
    -0.06
    igar
    -0.06
    POSITIVE LOGITS
    hotmail
    0.07
    Matchers
    0.07
    abbo
    0.06
     Hüs
    0.06
    ér
    0.06
    byn
    0.06
     Authorities
    0.06
    .opensource
    0.06
    .scalablytyped
    0.06
    apore
    0.06
    Activations Density 0.000%

    No Known Activations