© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 125774
    Prev
    Next
    INDEX
    Explanations

    phrases that express inclusion or emphasize specific groups

    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
     pÅĻiÄįemž
    -0.08
     ведÑĮ
    -0.07
    gaard
    -0.07
    аном
    -0.07
    tempt
    -0.07
    although
    -0.07
    orem
    -0.07
    дап
    -0.07
    sg
    -0.07
    tes
    -0.06
    POSITIVE LOGITS
    )
    0.08
     _______,
    0.08
     ones
    0.07
    ï¼īãģ¯
    0.07
    )를
    0.07
    ients
    0.07
     _{}
    0.07
     [])
    0.07
    !!,
    0.07
    (""),
    0.07
    Activations Density 0.041%

    No Known Activations