© 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. 90842
    Prev
    Next
    INDEX
    Explanations

    terms associated with success and accomplishment

    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
     Dude
    -0.08
    ÑĪев
    -0.07
     Dumpster
    -0.07
     Duc
    -0.07
    WindowState
    -0.07
    uo
    -0.07
    è¦ĭ
    -0.06
     danmark
    -0.06
     gib
    -0.06
     gar
    -0.06
    POSITIVE LOGITS
    idar
    0.06
    iterr
    0.06
    odel
    0.06
     regarding
    0.06
    erno
    0.06
    iment
    0.06
    atter
    0.06
     Us
    0.06
    erval
    0.06
     Moy
    0.06
    Activations Density 0.033%

    No Known Activations