© 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. 3748
    Prev
    Next
    INDEX
    Explanations

    phrases indicating quantities or counts

    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
    絶
    -0.08
    irie
    -0.08
    βο
    -0.07
    uder
    -0.07
     zbo
    -0.07
    ctp
    -0.07
    ç»Ŀ
    -0.07
    ooke
    -0.07
     arada
    -0.07
    abwe
    -0.07
    POSITIVE LOGITS
     three
    0.08
     two
    0.07
     four
    0.07
     several
    0.07
     six
    0.06
    icie
    0.06
    three
    0.06
     dozen
    0.05
     seven
    0.05
     upper
    0.05
    Activations Density 0.006%

    No Known Activations