© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 1462
    Prev
    Next
    INDEX
    Explanations

    components related to products or physical items

    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
    .sul
    -0.08
    uler
    -0.08
    illard
    -0.07
    ëĭĪëĭ¤
    -0.07
    inha
    -0.07
    ìľ¡
    -0.07
     FLAGS
    -0.07
    Flags
    -0.07
    ey
    -0.07
    cheid
    -0.07
    POSITIVE LOGITS
    /front
    0.08
     syndrome
    0.07
     and
    0.07
    ala
    0.06
    sg
    0.06
     Syndrome
    0.06
     getopt
    0.06
    ammen
    0.06
    á
    0.06
    ReuseIdentifier
    0.05
    Activations Density 0.017%

    No Known Activations