© 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. 125653
    Prev
    Next
    INDEX
    Explanations

    phrases indicating locations or sources related to information

    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
     themselves
    -0.08
    .sap
    -0.07
     and
    -0.07
    äºĽ
    -0.06
    .lesson
    -0.06
    AndPassword
    -0.06
     dor
    -0.06
     throughout
    -0.06
     automát
    -0.06
     are
    -0.06
    POSITIVE LOGITS
     someone
    0.12
     somebody
    0.12
    someone
    0.10
     nÃło
    0.10
    Someone
    0.09
     alguien
    0.09
     Someone
    0.08
    (s
    0.08
     jemand
    0.08
     Somebody
    0.07
    Activations Density 0.071%

    No Known Activations