© 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. 15-LLAMASCOPE-RES-131K
    11. 103717
    Prev
    Next
    INDEX
    Explanations

    phrases related to performance metrics or observations within a social context

    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
    ø
    -0.06
     Ngb
    -0.06
     vig
    -0.06
    ookies
    -0.06
    oky
    -0.05
     cul
    -0.05
    ysi
    -0.05
    ogenous
    -0.05
    holds
    -0.05
     guess
    -0.05
    POSITIVE LOGITS
     noticed
    0.11
    noticed
    0.10
     Noticed
    0.10
     Notice
    0.08
     noticing
    0.08
     notices
    0.08
    SED
    0.07
    Notice
    0.07
     notice
    0.07
    notice
    0.07
    Activations Density 0.047%

    No Known Activations