© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 77576
    Prev
    Next
    INDEX
    Explanations

    elements related to user interaction and system functionalities

    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
    æ§
    -0.07
    Ä©
    -0.07
    ilion
    -0.07
    kánÃŃ
    -0.07
    igi
    -0.07
    .microsoft
    -0.07
    ãĥ¼ãĥĪ
    -0.07
    amaz
    -0.07
    TRS
    -0.07
    urd
    -0.07
    POSITIVE LOGITS
     users
    0.10
     user
    0.09
    user
    0.08
    -users
    0.08
     skilled
    0.07
     team
    0.07
     Users
    0.07
     teams
    0.07
    çĶ¨æĪ·
    0.07
     USERS
    0.07
    Activations Density 0.040%

    No Known Activations