© 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. 57747
    Prev
    Next
    INDEX
    Explanations

    instances of the word "follow" and its variations

    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
     Duck
    -0.09
     duck
    -0.08
    hon
    -0.07
    ÑģÑıг
    -0.06
    uck
    -0.06
    duck
    -0.06
     còn
    -0.06
    æĹģ
    -0.06
    稿
    -0.06
     away
    -0.06
    POSITIVE LOGITS
    elez
    0.07
    valuator
    0.07
    277
    0.07
    WORDS
    0.07
    ekler
    0.07
    erb
    0.06
    ingly
    0.06
    ãĤ¤ãĤº
    0.06
     mans
    0.06
     suit
    0.06
    Activations Density 0.011%

    No Known Activations