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. 43385
    Prev
    Next
    INDEX
    Explanations

    identifiers or names associated with specific individuals, concepts, or entities

    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
     ITE
    -0.10
    ITE
    -0.09
    ETS
    -0.09
    erti
    -0.09
    etti
    -0.08
    etes
    -0.08
    YTE
    -0.08
    ITES
    -0.08
    RTC
    -0.08
    ERT
    -0.08
    POSITIVE LOGITS
    tat
    0.20
     Tat
    0.19
     tat
    0.18
    lat
    0.18
    atat
    0.18
    itat
    0.17
     lat
    0.16
    fat
    0.16
    dat
    0.15
    etat
    0.15
    Activations Density 0.022%

    No Known Activations