© 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. 17-LLAMASCOPE-RES-131K
    11. 86716
    Prev
    Next
    INDEX
    Explanations

    instances of formatted mathematical symbols or programming syntax

    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
    voie
    -0.07
    ustr
    -0.07
    CAS
    -0.06
    ÑĢиÑģÑĤи
    -0.06
    íķŃ
    -0.06
     normals
    -0.06
    enty
    -0.06
    unk
    -0.06
    TemplateName
    -0.06
    radient
    -0.06
    POSITIVE LOGITS
    arro
    0.07
    elli
    0.07
    udeau
    0.07
    оÑĢоÑĪ
    0.07
     dig
    0.06
    åĬĽ
    0.06
    .unbind
    0.06
    ary
    0.06
    dig
    0.06
    strom
    0.06
    Activations Density 0.008%

    No Known Activations