© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 93999
    Prev
    Next
    INDEX
    Explanations

    references to academic years in school or programs

    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
    ãģ¾ãģŁ
    -0.07
    γη
    -0.06
    plib
    -0.06
    angkan
    -0.06
     bored
    -0.06
    èŀ
    -0.06
     Gig
    -0.06
     ersten
    -0.06
    SqlServer
    -0.06
    mojom
    -0.06
    POSITIVE LOGITS
    -olds
    0.07
    longleftrightarrow
    0.07
    WP
    0.07
    edback
    0.06
    imore
    0.06
    itis
    0.06
    clus
    0.06
    onder
    0.06
    tons
    0.06
    imizde
    0.06
    Activations Density 0.013%

    No Known Activations