© 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. 126736
    Prev
    Next
    INDEX
    Explanations

    references to games or gaming elements, especially related to war themes

    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
     fund
    -0.07
    inspection
    -0.06
    adora
    -0.06
    868
    -0.06
     Swords
    -0.06
    ovolta
    -0.06
     Magical
    -0.06
     Dungeon
    -0.06
     MST
    -0.05
    784
    -0.05
    POSITIVE LOGITS
    iris
    0.08
    Tac
    0.08
    ghost
    0.07
    _TAC
    0.07
    ยà¸ĩ
    0.07
    ahlen
    0.07
    antanamo
    0.07
    ÑĢаÑĤи
    0.07
     kuk
    0.07
     Gauss
    0.07
    Activations Density 0.003%

    No Known Activations