© 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. 31322
    Prev
    Next
    INDEX
    Explanations

    references to interviews and public statements by individuals

    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
    abis
    -0.06
     kvin
    -0.06
    rieben
    -0.06
     Ù¾ÛĮÚ©
    -0.06
     Anonymous
    -0.06
    ãĥ¼ãĥī
    -0.06
     pend
    -0.06
    erts
    -0.06
    .enqueue
    -0.06
    estring
    -0.06
    POSITIVE LOGITS
     interview
    0.20
     interviews
    0.18
     Interview
    0.17
    Interview
    0.16
     interviewed
    0.16
     entrev
    0.15
     interviewer
    0.15
     Interviews
    0.14
     speech
    0.14
     Speech
    0.12
    Activations Density 0.109%

    No Known Activations