© 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. 5-LLAMASCOPE-RES-131K
    11. 126461
    Prev
    Next
    INDEX
    Explanations

    mentions of environmental impact and related sustainability efforts

    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
    517
    -0.06
    ιλο
    -0.06
    ä¾į
    -0.06
     Micha
    -0.06
    {{
    -0.05
    usi
    -0.05
     eventually
    -0.05
    827
    -0.05
    etta
    -0.05
    oids
    -0.05
    POSITIVE LOGITS
    antage
    0.07
    \Doctrine
    0.07
    bsolute
    0.07
    æĹĭ
    0.07
    quel
    0.07
    ADDE
    0.07
    AllWindows
    0.07
     Buccane
    0.07
    angler
    0.07
    illis
    0.06
    Activations Density 0.019%

    No Known Activations