© 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. 3182
    Prev
    Next
    INDEX
    Explanations

    corporate entities and business-related transactions

    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
    roit
    -0.08
    dera
    -0.08
     bracket
    -0.07
    shima
    -0.07
    _CSR
    -0.07
    áng
    -0.07
    rosso
    -0.07
    оÑĢоÑĤ
    -0.07
    uchos
    -0.07
    üf
    -0.07
    POSITIVE LOGITS
    ãĥĭãĥ¼
    0.06
     (“
    0.06
    recent
    0.06
    OLL
    0.06
    annel
    0.06
    owned
    0.06
     recently
    0.05
    oleÄį
    0.05
    qx
    0.05
     Cardinal
    0.05
    Activations Density 0.012%

    No Known Activations