© 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. 74658
    Prev
    Next
    INDEX
    Explanations

    references to sources of information or news reporting

    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
     Stored
    -0.07
     |--------------------------------------------------------------------------↵
    -0.06
    avra
    -0.06
     Gap
    -0.06
    оÑĢе
    -0.06
    дÑĢеÑģ
    -0.06
    ROADCAST
    -0.06
    imple
    -0.06
     coerc
    -0.06
    аÑĪа
    -0.06
    POSITIVE LOGITS
     sources
    0.15
     information
    0.14
     source
    0.12
    sources
    0.12
    information
    0.12
     Sources
    0.12
     intelligence
    0.11
    æĥħåł±
    0.11
    /sources
    0.11
     info
    0.11
    Activations Density 0.087%

    No Known Activations