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

    Neuronpedia

    APICircuit 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. 31-LLAMASCOPE-RES-131K
    6. 43620
    Prev
    Next
    INDEX
    Explanations

    key findings and associations in scientific studies

    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
    enthal
    -0.08
    AMED
    -0.07
    ÑįÑĤ
    -0.07
    ãĥĨãĥ«
    -0.07
     Auswahl
    -0.07
    boru
    -0.06
    ometr
    -0.06
    ampp
    -0.06
    á»ijt
    -0.06
    acket
    -0.06
    POSITIVE LOGITS
     supports
    0.10
     tent
    0.10
     support
    0.09
     suggests
    0.09
     suggest
    0.09
     implic
    0.09
     prelim
    0.09
     warrants
    0.09
     suggested
    0.09
     raises
    0.09
    Activations Density 0.058%

    No Known Activations