© 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. 76287
    Prev
    Next
    INDEX
    Explanations

    terms associated with specific industries or professional sectors

    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
    elo
    -0.07
    emark
    -0.06
    inet
    -0.06
    irt
    -0.06
     Stamp
    -0.06
    egis
    -0.06
    ÑĤаж
    -0.06
    iaz
    -0.06
    ovsky
    -0.06
    ãĥ«ãĥķ
    -0.06
    POSITIVE LOGITS
    人ãģ¯
    0.09
    Ư
    0.07
    ober
    0.07
    人ãģĮ
    0.07
    eken
    0.07
    ARSE
    0.07
    759
    0.07
    addElement
    0.06
    615
    0.06
    ết
    0.06
    Activations Density 0.072%

    No Known Activations