© 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. 61565
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions and movements in a narrative context

    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
    uts
    -0.07
     consec
    -0.06
    ieve
    -0.06
    ieves
    -0.06
     cries
    -0.06
    421
    -0.06
    743
    -0.06
     dostan
    -0.06
    rea
    -0.06
     cry
    -0.06
    POSITIVE LOGITS
    fork
    0.07
    Äįil
    0.07
    èĵ
    0.07
    DialogTitle
    0.07
    peare
    0.07
    haar
    0.07
    stice
    0.06
    Crud
    0.06
    ValueCollection
    0.06
    razil
    0.06
    Activations Density 0.034%

    No Known Activations