© 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. 75218
    Prev
    Next
    INDEX
    Explanations

    references to holidays and their impact on business operations

    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
    ASN
    -0.07
    artz
    -0.07
    ERA
    -0.07
    vailable
    -0.07
    .CreateIndex
    -0.07
    Ñİк
    -0.07
    ocab
    -0.06
    .matcher
    -0.06
    hta
    -0.06
    UBLE
    -0.06
    POSITIVE LOGITS
    eno
    0.06
    acci
    0.06
    erville
    0.06
    acky
    0.06
     during
    0.06
    ãĤ¸ãĤ§
    0.05
    asca
    0.05
     durante
    0.05
    OLID
    0.05
     esteem
    0.05
    Activations Density 0.004%

    No Known Activations