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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 31-LLAMASCOPE-RES-131K
    6. 44156
    Prev
    Next
    INDEX
    Explanations

    terms associated with personal history and social 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
     oneself
    -0.07
     ourselves
    -0.07
     yourself
    -0.07
     yourselves
    -0.07
    본
    -0.06
     доÑĢ
    -0.06
    conte
    -0.06
    whose
    -0.06
     myself
    -0.06
     susceptible
    -0.05
    POSITIVE LOGITS
    iveness
    0.11
     vis
    0.10
     abilities
    0.10
     regarding
    0.10
    iness
    0.09
    fulness
    0.09
    lessness
    0.09
     toward
    0.09
     towards
    0.09
    (s
    0.09
    Activations Density 0.186%

    No Known Activations