© 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. 71678
    Prev
    Next
    INDEX
    Explanations

    references to website structure or content organization

    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
    ares
    -0.06
    ion
    -0.06
     multipart
    -0.06
    ium
    -0.06
    hazi
    -0.05
     panc
    -0.05
    ians
    -0.05
    m
    -0.05
    ilde
    -0.05
    l
    -0.05
    POSITIVE LOGITS
    ymes
    0.08
    Smarty
    0.08
    strand
    0.08
    ayi
    0.07
    COLUMN
    0.07
    yer
    0.07
    erokee
    0.07
     Ñģеб
    0.07
    Drupal
    0.07
    WEBPACK
    0.07
    Activations Density 0.002%

    No Known Activations