© 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. 74569
    Prev
    Next
    INDEX
    Explanations

    phrases related to advisement and approval processes

    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
    -related
    -0.06
    jie
    -0.06
    ubs
    -0.06
     also
    -0.06
    gard
    -0.06
    icker
    -0.06
     oby
    -0.06
    589
    -0.06
    sov
    -0.06
    alte
    -0.06
    POSITIVE LOGITS
    ctors
    0.09
    ctor
    0.07
    ectors
    0.07
    tempts
    0.07
     vein
    0.06
    _Collections
    0.06
    ector
    0.06
    çĸ¾
    0.06
     Batt
    0.06
    imetype
    0.06
    Activations Density 0.017%

    No Known Activations