Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 40562
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    agli
    -0.07
    aż
    -0.07
    alc
    -0.07
    ec
    -0.07
    eÄį
    -0.07
    .cs
    -0.06
    èĵ
    -0.06
    etch
    -0.06
    _many
    -0.06
    OUCH
    -0.06
    POSITIVE LOGITS
    imu
    0.07
    rossover
    0.06
    ihar
    0.06
     spons
    0.06
    gan
    0.06
     instead
    0.06
    idos
    0.06
    omor
    0.06
     preseason
    0.06
     ëĤ´ëł¤
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.