© 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. 84991
    Prev
    Next
    INDEX
    Explanations

    verbs indicating actionable processes or decisions

    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
     ???
    -0.07
    ackages
    -0.06
     ??
    -0.06
    anyak
    -0.06
     closely
    -0.06
    å¾Īå¤ļ
    -0.06
     ?????
    -0.06
    ask
    -0.06
    -font
    -0.06
     gro
    -0.06
    POSITIVE LOGITS
    kaar
    0.08
     vlastnÄĽ
    0.08
     effectively
    0.07
     вообÑīе
    0.07
     Jaune
    0.07
    (æľ¨
    0.06
     ÚĨÙĨÛĮÙĨ
    0.06
    _FA
    0.06
    exion
    0.06
    &&!
    0.06
    Activations Density 0.040%

    No Known Activations