© 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. 76815
    Prev
    Next
    INDEX
    Explanations

    referenced body parts and their associated conditions

    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
    morgan
    -0.07
    ictions
    -0.07
    illance
    -0.07
    гÑĥ
    -0.07
    ứng
    -0.07
    .removeFrom
    -0.07
    hip
    -0.07
    urger
    -0.07
    tright
    -0.07
    ãĤ¤ãĥ³ãĥĪ
    -0.07
    POSITIVE LOGITS
    -centric
    0.08
    /body
    0.07
    eh
    0.07
    éĻħ
    0.07
    eren
    0.06
    æ³ģ
    0.06
    -region
    0.06
     Mattis
    0.06
    -focused
    0.06
    -owner
    0.06
    Activations Density 0.023%

    No Known Activations