© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 125969
    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
     asker
    -0.06
    .fm
    -0.06
     Stam
    -0.06
     '[
    -0.06
    PRECATED
    -0.06
    _NR
    -0.06
     nonprofits
    -0.06
    (_:
    -0.05
    ÂŃi
    -0.05
    its
    -0.05
    POSITIVE LOGITS
     inclusive
    0.07
    èĥ½å¤Ł
    0.07
     persons
    0.07
    persons
    0.06
    пÑĢа
    0.06
     Bernardino
    0.06
    jedn
    0.06
    beit
    0.06
    ooks
    0.06
    Persons
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.