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. 22-LLAMASCOPE-RES-131K
    6. 5616
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating possibility and obligation

    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
    ardy
    -0.08
     Sims
    -0.06
    ãĥ³ãĥĩ
    -0.06
    \\\\
    -0.06
    vvm
    -0.06
    achu
    -0.06
     yourselves
    -0.06
    amburg
    -0.06
    ilan
    -0.06
     bol
    -0.05
    POSITIVE LOGITS
    .bc
    0.07
    ĨĴ
    0.07
    ervers
    0.07
    HOOK
    0.07
    ÙħاÙĦ
    0.07
    NamedQuery
    0.07
    CLU
    0.07
    ÂŃi
    0.06
    SWG
    0.06
     anyhow
    0.06
    Activations Density 0.085%

    No Known Activations