© 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. 17-LLAMASCOPE-RES-131K
    6. 93463
    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
    å¹³æĪIJ
    -0.09
    orden
    -0.08
    ittel
    -0.08
    _firestore
    -0.08
    нож
    -0.07
     Fucking
    -0.07
     Bilim
    -0.07
     nalez
    -0.07
    )((((
    -0.07
    .au
    -0.07
    POSITIVE LOGITS
     "
    0.10
     partly
    0.08
     
    0.08
     "'
    0.07
    ,
    0.06
     —
    0.06
     new
    0.06
     tens
    0.06
     details
    0.06
     using
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.