© 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. 84124
    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
    alytics
    -0.07
    842
    -0.06
    mh
    -0.06
    eton
    -0.06
    é©
    -0.06
    tul
    -0.06
    esture
    -0.06
    resse
    -0.06
     drive
    -0.06
    xFFFFFF
    -0.06
    POSITIVE LOGITS
     soaked
    0.07
     rais
    0.07
     sop
    0.07
    ¶Į
    0.07
     Packet
    0.06
    thood
    0.06
     packet
    0.06
     soak
    0.06
     Functional
    0.06
    .goal
    0.06
    Activations Density 0.058%

    No Known Activations