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. 9-LLAMASCOPE-RES-131K
    6. 96101
    Prev
    Next
    INDEX
    Explanations

    references to VIP access or experience

    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
    erli
    -0.07
    /function
    -0.07
    olicit
    -0.07
    /topics
    -0.07
    hlen
    -0.07
    ixo
    -0.06
     DialogInterface
    -0.06
    isto
    -0.06
    ill
    -0.06
    immer
    -0.06
    POSITIVE LOGITS
    imized
    0.08
    oval
    0.08
    blem
    0.07
    olini
    0.07
    ÑĦи
    0.06
    åĮĸ
    0.06
    Ľ°
    0.06
     isc
    0.06
    ÑĢиз
    0.06
    ãĥĭãĥ¥
    0.06
    Activations Density 0.002%

    No Known Activations