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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 103759
    Prev
    Next
    INDEX
    Explanations

    mentions of places, especially universities

    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
     Poz
    -0.06
     Dann
    -0.06
     Rut
    -0.06
    oft
    -0.05
    byt
    -0.05
     Heller
    -0.05
    695
    -0.05
     withStyles
    -0.05
    egrator
    -0.05
    oe
    -0.05
    POSITIVE LOGITS
    bens
    0.08
    áty
    0.07
    енÑģ
    0.07
    (íģ¬ê¸°
    0.07
     Relief
    0.07
    edio
    0.06
    eced
    0.06
    chner
    0.06
    ÐIJÑĢÑħÑĸв
    0.06
    ansom
    0.06
    Activations Density 0.023%

    No Known Activations