© 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. 70880
    Prev
    Next
    INDEX
    Explanations

    references to testing frameworks or structures 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
    ensis
    -0.07
    nda
    -0.07
    ordova
    -0.07
    orners
    -0.07
    kla
    -0.06
    opal
    -0.06
    ogan
    -0.06
    orgia
    -0.06
    atsby
    -0.06
     kla
    -0.06
    POSITIVE LOGITS
    ани
    0.07
    کار
    0.06
     Garn
    0.06
    Attachments
    0.06
    SocketAddress
    0.06
    arden
    0.06
    sik
    0.06
    ÐĿаÑģ
    0.06
     æĿ¡
    0.06
    amaño
    0.06
    Activations Density 0.000%

    No Known Activations