© 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. 15-LLAMASCOPE-RES-131K
    11. 61791
    Prev
    Next
    INDEX
    Explanations

    references to drugs and their related terminology, particularly highlighting the term "soma" and its implications

    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
    ÑĢедиÑĤ
    -0.07
    ont
    -0.06
    ONT
    -0.06
     ag
    -0.06
    antas
    -0.06
    316
    -0.06
    ãĥĥãĥĦ
    -0.06
    åłĤ
    -0.06
    ie
    -0.06
    rey
    -0.05
    POSITIVE LOGITS
    #
    0.08
    isphere
    0.07
    ucc
    0.07
    eldorf
    0.07
    ROKE
    0.07
    scriptId
    0.07
    .PerformLayout
    0.07
    ATUS
    0.07
     Hüs
    0.07
    usra
    0.07
    Activations Density 0.005%

    No Known Activations