© 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. 1027
    Prev
    Next
    INDEX
    Explanations

    mathematical or programming concepts related to vectors and matrices

    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
     whe
    -0.06
     Franco
    -0.06
    maj
    -0.06
     Wheel
    -0.06
    Wheel
    -0.06
    .kode
    -0.06
    Wave
    -0.06
     Satellite
    -0.06
    _MED
    -0.06
    aset
    -0.06
    POSITIVE LOGITS
     Norm
    0.08
    enties
    0.08
    rada
    0.07
    Norm
    0.07
    WithPath
    0.07
    contri
    0.06
    ince
    0.06
    calc
    0.06
    float
    0.06
    ë°į
    0.06
    Activations Density 0.096%

    No Known Activations