© 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. 77285
    Prev
    Next
    INDEX
    Explanations

    text that discusses personal experiences and narratives

    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
    eldom
    -0.07
    arg
    -0.07
     Hans
    -0.06
    asu
    -0.06
    çĶ
    -0.06
     GDK
    -0.06
    args
    -0.06
    AREN
    -0.06
    .impl
    -0.06
    idot
    -0.06
    POSITIVE LOGITS
     interviewer
    0.09
     interview
    0.09
     describe
    0.08
     describes
    0.08
     entrev
    0.07
     Interview
    0.07
     remin
    0.07
    è«ĩ
    0.07
     descriptions
    0.07
    Interview
    0.07
    Activations Density 0.009%

    No Known Activations