Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71238
    Prev
    Next
    INDEX
    Explanations

    mentions of governance and permissions in a legal or formal context

    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
    élé
    -0.07
     æĻ´
    -0.07
    ierge
    -0.07
    Ìĥ
    -0.07
    ERGE
    -0.07
    å±±å¸Ĥ
    -0.07
    ATEGORIES
    -0.07
    conti
    -0.06
    phony
    -0.06
    259
    -0.06
    POSITIVE LOGITS
    âĹİ
    0.07
     Budd
    0.06
    anko
    0.06
     Crane
    0.06
    OVE
    0.06
     Southern
    0.06
     Vect
    0.06
    ilton
    0.06
     Germ
    0.05
     Wade
    0.05
    Activations Density 0.001%

    No Known Activations