© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 88175
    Prev
    Next
    INDEX
    Explanations

    mentions of anxiety disorders

    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
     Wong
    -0.09
    _UD
    -0.08
    emoc
    -0.07
    esel
    -0.07
    rect
    -0.07
    unctuation
    -0.07
    lesc
    -0.06
    -fi
    -0.06
    ãģĺãĤĥ
    -0.06
    -Fi
    -0.06
    POSITIVE LOGITS
    NSSet
    0.06
     Company
    0.06
    uez
    0.06
    ÏĦÏħ
    0.06
    insky
    0.06
    bah
    0.06
    ë¶Ģ
    0.06
    hq
    0.06
    longleftrightarrow
    0.05
     FAIL
    0.05
    Activations Density 0.000%

    No Known Activations