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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 84302
    Prev
    Next
    INDEX
    Explanations

    instances of personal and professional relationships

    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
    eton
    -0.08
     tomorrow
    -0.08
    kad
    -0.07
    asta
    -0.06
    rary
    -0.06
    alah
    -0.06
    è
    -0.06
    oppers
    -0.06
    адÑĥ
    -0.06
    dictions
    -0.06
    POSITIVE LOGITS
     idea
    0.10
     contacts
    0.09
    idea
    0.08
    contacts
    0.08
     éĹ
    0.08
     ideas
    0.07
     coinc
    0.07
     contact
    0.07
     Idea
    0.07
     contacted
    0.07
    Activations Density 0.091%

    No Known Activations