© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 118545
    Prev
    Next
    INDEX
    Explanations

    references to community-driven content and player contributions in game development

    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
    .
    -0.06
    /setup
    -0.06
     ti
    -0.06
    ð
    -0.06
     Gaming
    -0.05
    ,
    -0.05
    (SP
    -0.05
     Wilderness
    -0.05
     Bracket
    -0.05
    quired
    -0.05
    POSITIVE LOGITS
    åĪĽ
    0.09
     creations
    0.08
     creation
    0.08
     Creation
    0.08
    anje
    0.08
    pekt
    0.07
    Creation
    0.07
    764
    0.07
    .effects
    0.07
    -create
    0.07
    Activations Density 0.007%

    No Known Activations