© 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. 15-LLAMASCOPE-RES-131K
    6. 89951
    Prev
    Next
    INDEX
    Explanations

    keywords related to exceptions and error handling in programming

    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
    .scalablytyped
    -0.09
    ÑĢава
    -0.08
    pest
    -0.08
    обов
    -0.08
    ysa
    -0.08
    .Apis
    -0.07
    imli
    -0.07
    EdgeInsets
    -0.07
    ÑĢиÑĤи
    -0.07
    ERCHANT
    -0.07
    POSITIVE LOGITS
    s
    0.07
    e
    0.07
    esium
    0.06
    al
    0.06
     obsc
    0.06
    le
    0.06
    i
    0.06
    ne
    0.06
    137
    0.06
    lite
    0.06
    Activations Density 0.001%

    No Known Activations