© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 118323
    Prev
    Next
    INDEX
    Explanations

    references to comparisons and contrasts in relation to specific subjects

    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
    al
    -0.06
    asi
    -0.06
    eg
    -0.06
    оÑĢдин
    -0.06
     NavParams
    -0.06
    pard
    -0.06
    ADED
    -0.06
    arel
    -0.05
    kind
    -0.05
    postalcode
    -0.05
    POSITIVE LOGITS
    724
    0.07
     original
    0.07
     regular
    0.07
     asıl
    0.07
     originals
    0.07
    .crop
    0.07
    ooke
    0.07
     оÑĢиг
    0.06
    kara
    0.06
    erm
    0.06
    Activations Density 0.094%

    No Known Activations