© 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. 85084
    Prev
    Next
    INDEX
    Explanations

    phrases that address or engage the reader directly

    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
     гÑĢом
    -0.07
    :animated
    -0.07
    emean
    -0.07
    é̏
    -0.07
    lace
    -0.07
    plorer
    -0.07
    jn
    -0.06
    ,www
    -0.06
    urger
    -0.06
    ÐIJÑĢÑħÑĸв
    -0.06
    POSITIVE LOGITS
    Ñįй
    0.06
    OTH
    0.06
     Nose
    0.06
    489
    0.06
    \Bridge
    0.05
    deme
    0.05
     Cargo
    0.05
    wa
    0.05
    otonin
    0.05
    819
    0.05
    Activations Density 0.020%

    No Known Activations