© 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. 15-LLAMASCOPE-RES-131K
    11. 90274
    Prev
    Next
    INDEX
    Explanations

    HTML tags and their attributes

    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
     adj
    -0.07
    ãĥijãĥ³
    -0.06
    bery
    -0.06
    esel
    -0.06
    nyder
    -0.06
     CRS
    -0.06
    ttp
    -0.06
    é¡
    -0.06
    SSIP
    -0.06
    (æĹ¥
    -0.06
    POSITIVE LOGITS
    atile
    0.08
    ois
    0.07
    AttributeValue
    0.06
     kaz
    0.06
    fos
    0.06
    .Concurrent
    0.06
     knock
    0.06
    upported
    0.06
    ierz
    0.06
    LEX
    0.06
    Activations Density 0.000%

    No Known Activations