© 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. 125948
    Prev
    Next
    INDEX
    Explanations

    instances of the word "across" and related terms suggesting movement or discovery

    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
    oret
    -0.08
    undler
    -0.07
    immel
    -0.07
    chine
    -0.07
    /XML
    -0.07
    ldr
    -0.07
    ints
    -0.06
    ÑĦ
    -0.06
    /as
    -0.06
    reira
    -0.06
    POSITIVE LOGITS
    icut
    0.06
     ways
    0.06
     nhau
    0.06
    ery
    0.06
    sing
    0.06
    ordin
    0.06
    yer
    0.06
    midt
    0.06
     exp
    0.06
     situations
    0.06
    Activations Density 0.004%

    No Known Activations