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. 77256
    Prev
    Next
    INDEX
    Explanations

    entities related to people and events in a social 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
    (çģ«
    -0.08
    åĦĦ
    -0.07
    ãİ
    -0.07
     IPT
    -0.07
    (éĩij
    -0.07
     McCart
    -0.07
    (æ°´
    -0.07
    ATAL
    -0.07
     rocker
    -0.07
    security
    -0.07
    POSITIVE LOGITS
     DJ
    0.11
     dance
    0.09
     DJs
    0.09
     dj
    0.09
     remix
    0.08
    909
    0.08
    DJ
    0.08
     Remix
    0.08
     danced
    0.08
     dub
    0.07
    Activations Density 0.130%

    No Known Activations