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. 71340
    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
    "urls
    -0.06
     etc
    -0.06
    .scalablytyped
    -0.06
    olla
    -0.06
    'gc
    -0.06
    aram
    -0.06
    .appspot
    -0.06
    ottes
    -0.06
     info
    -0.06
    ãĥ¼ãĥ©
    -0.06
    POSITIVE LOGITS
    aggi
    0.07
    captures
    0.06
    inclusive
    0.06
    اÙĬÙĨ
    0.06
    اÙģÙĬ
    0.06
    omba
    0.06
    kees
    0.06
    ÙĪÙĬÙĥ
    0.06
     surviv
    0.06
    .walk
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.