© 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. 119560
    Prev
    Next
    INDEX
    Explanations

    descriptors of relationships and individual characteristics

    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
    ives
    -0.08
    _Tis
    -0.08
    uales
    -0.08
    odate
    -0.07
    ió
    -0.07
    ityEngine
    -0.07
    orre
    -0.07
    iams
    -0.07
    argin
    -0.07
    emek
    -0.07
    POSITIVE LOGITS
     sister
    0.08
     partner
    0.07
     brother
    0.07
     twin
    0.07
     wife
    0.07
     followers
    0.07
     partners
    0.06
     counterpart
    0.06
     friends
    0.06
     collabor
    0.06
    Activations Density 0.021%

    No Known Activations