Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5355
    Prev
    Next
    INDEX
    Explanations

    phrases related to updates or modifications in context

    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
    itti
    -0.07
    sville
    -0.07
    entlich
    -0.07
    slu
    -0.07
    иÑĤи
    -0.06
    ấu
    -0.06
    sWith
    -0.06
    jte
    -0.06
    سر
    -0.06
     ми
    -0.06
    POSITIVE LOGITS
    iolet
    0.07
     Charl
    0.07
    pat
    0.06
     
    0.06
    rij
    0.06
     βά
    0.06
    istics
    0.05
    raf
    0.05
    Quit
    0.05
    umbs
    0.05
    Activations Density 0.002%

    No Known Activations