© 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. 85358
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant occurrences 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
    steder
    -0.06
     -------------------------------------------------------------------------↵
    -0.06
    INGTON
    -0.06
     ÑģÑĤав
    -0.06
    olik
    -0.06
     ãĤ½
    -0.06
    座
    -0.06
     cigaret
    -0.06
    sted
    -0.06
    æĥij
    -0.06
    POSITIVE LOGITS
    uality
    0.11
    275
    0.08
     nÃło
    0.07
    èĥ¶
    0.07
    620
    0.07
    823
    0.07
    206
    0.07
     of
    0.06
    e
    0.06
     FindObjectOfType
    0.06
    Activations Density 0.002%

    No Known Activations