Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96296
    Prev
    Next
    INDEX
    Explanations

    words related to certification and accreditation processes

    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
    ä¸Ģ页
    -0.07
    SWEP
    -0.06
    abus
    -0.06
    еÑĤиÑĩ
    -0.06
     beh
    -0.06
     Adams
    -0.06
    vik
    -0.06
    ounc
    -0.06
    ertz
    -0.06
    vor
    -0.06
    POSITIVE LOGITS
     Hayden
    0.07
    bris
    0.07
    arl
    0.07
    borg
    0.07
    živ
    0.06
    ÏĦε
    0.06
    QRS
    0.06
    panion
    0.06
     Gle
    0.06
    Ìĥ
    0.06
    Activations Density 0.031%

    No Known Activations