© 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. 75714
    Prev
    Next
    INDEX
    Explanations

    references to visual representations or images in various contexts

    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
    ibs
    -0.11
    rych
    -0.09
     NavParams
    -0.08
    unan
    -0.08
    ilos
    -0.08
    åij³
    -0.08
    eyh
    -0.07
    ittal
    -0.07
    夫
    -0.07
    aload
    -0.07
    POSITIVE LOGITS
     of
    0.07
     floating
    0.07
    d
    0.07
    204
    0.06
     stick
    0.06
     image
    0.06
     Warren
    0.06
     Schmidt
    0.06
     --
    0.05
    779
    0.05
    Activations Density 0.014%

    No Known Activations