© 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. 40663
    Prev
    Next
    INDEX
    Explanations

    instructions or details related to gaming objectives and missions

    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
    ibal
    -0.08
    ourg
    -0.07
     Lage
    -0.07
    CREMENT
    -0.07
    mma
    -0.07
    ÙĨت
    -0.07
    ÏģÏį
    -0.07
    rema
    -0.07
    heten
    -0.07
    ูà¸Ĺ
    -0.07
    POSITIVE LOGITS
     dialogue
    0.08
    NPC
    0.07
     mission
    0.07
     Dialogue
    0.06
     speech
    0.06
     talk
    0.06
     conversation
    0.06
    IALOG
    0.06
     Speech
    0.06
    LP
    0.06
    Activations Density 0.018%

    No Known Activations