© 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. 15-LLAMASCOPE-RES-131K
    6. 26791
    Prev
    Next
    INDEX
    Explanations

    references to database or catalog information

    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
     
    -0.06
    ssi
    -0.06
    edi
    -0.06
    isson
    -0.06
    ivas
    -0.05
    sat
    -0.05
    old
    -0.05
    undra
    -0.05
     Luck
    -0.05
    seys
    -0.05
    POSITIVE LOGITS
    ignum
    0.08
    #__
    0.08
     @}
    0.07
    .xhtml
    0.07
     вок
    0.07
    ascus
    0.07
    سط
    0.07
     Tá»ķ
    0.07
     вед
    0.07
    CHANT
    0.07
    Activations Density 0.001%

    No Known Activations