© 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. 76641
    Prev
    Next
    INDEX
    Explanations

    instances of the word "and" indicating conjunctions or connections between ideas

    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
    addtogroup
    -0.08
    Äĥn
    -0.07
    AZE
    -0.07
     noreferrer
    -0.07
    exus
    -0.06
    agens
    -0.06
    ovit
    -0.06
    ieve
    -0.06
    ucher
    -0.06
    adesh
    -0.06
    POSITIVE LOGITS
    nbsp
    0.08
    enis
    0.07
     early
    0.07
    env
    0.07
    aire
    0.07
     Mane
    0.07
    AMP
    0.06
     Beyond
    0.06
     Env
    0.06
    ennes
    0.06
    Activations Density 0.030%

    No Known Activations