© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 40043
    Prev
    Next
    INDEX
    Explanations

    conjunctive phrases that emphasize connections and 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
    ando
    -0.06
    rush
    -0.06
    elez
    -0.06
    ERM
    -0.06
    ura
    -0.06
     <<-
    -0.06
    ermann
    -0.06
     Vog
    -0.06
    lush
    -0.06
     Spells
    -0.06
    POSITIVE LOGITS
     how
    0.13
    how
    0.10
     why
    0.10
    å¦Ĥä½ķ
    0.08
     what
    0.08
    //{{
    0.07
     cómo
    0.07
     ways
    0.07
     its
    0.07
    why
    0.07
    Activations Density 0.028%

    No Known Activations