© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 30021
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "developments."

    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
    isson
    -0.08
    ãģĦãĤĭ
    -0.07
    olumn
    -0.07
    à¥Īà¤Ĺ
    -0.07
    blr
    -0.07
     bec
    -0.07
    _srv
    -0.07
    ogen
    -0.07
    HING
    -0.07
    NSS
    -0.07
    POSITIVE LOGITS
     developments
    0.08
    /latest
    0.07
     elsewhere
    0.07
    hest
    0.07
    ments
    0.07
    ements
    0.07
     Dash
    0.06
    ings
    0.06
    /new
    0.06
     ìĤ¬íķŃ
    0.06
    Activations Density 0.006%

    No Known Activations