© 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. 87087
    Prev
    Next
    INDEX
    Explanations

    programming-related terminology and data types

    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
    ample
    -0.07
    oine
    -0.07
    .eng
    -0.07
    oyo
    -0.07
    emple
    -0.07
    oload
    -0.07
    (çģ«
    -0.07
    706
    -0.06
     cá»Ļng
    -0.06
    untu
    -0.06
    POSITIVE LOGITS
     lightweight
    0.07
    ãĥ©ãĤ¤ãĥĪ
    0.07
     Natal
    0.06
     Guar
    0.06
     Heal
    0.06
     McMahon
    0.06
    åIJĪãĤıãģĽ
    0.06
    _SN
    0.06
    icine
    0.05
    Rew
    0.05
    Activations Density 0.003%

    No Known Activations