© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76772
    Prev
    Next
    INDEX
    Explanations

    collaborations and partnerships in various 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
    ằm
    -0.07
    dain
    -0.07
    ABCDEFG
    -0.07
    ÑĤаж
    -0.07
    atin
    -0.07
    tain
    -0.07
    onte
    -0.07
    LOUR
    -0.07
    anzi
    -0.07
    .mousePosition
    -0.07
    POSITIVE LOGITS
     partner
    0.12
     partners
    0.10
    partner
    0.09
     Partner
    0.08
     local
    0.08
     network
    0.07
    partners
    0.06
    Partner
    0.06
     other
    0.06
     individuals
    0.06
    Activations Density 0.028%

    No Known Activations