© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 126557
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases related to significant actions or events

    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
    u
    -0.06
     spl
    -0.06
    pl
    -0.06
    pair
    -0.06
    loub
    -0.06
    OPY
    -0.06
     cav
    -0.06
    .âĢ¦
    -0.05
    Hint
    -0.05
    _hint
    -0.05
    POSITIVE LOGITS
    Ïĩι
    0.08
    .scalablytyped
    0.08
     ÑĦÑĥнда
    0.08
    妮
    0.07
    ',//
    0.07
    .binding
    0.07
    Ñģклад
    0.07
    _stdio
    0.07
    #ad
    0.07
    _________________↵↵
    0.07
    Activations Density 0.002%

    No Known Activations