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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5343
    Prev
    Next
    INDEX
    Explanations

    references to historical locations or landmarks

    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
    adium
    -0.06
    UTC
    -0.06
     Stadium
    -0.06
     Flames
    -0.06
     rekl
    -0.05
    ÅĻet
    -0.05
     Durant
    -0.05
     SWAT
    -0.05
     пÑĢиÑĤ
    -0.05
    obot
    -0.05
    POSITIVE LOGITS
     forts
    0.13
     fort
    0.12
    fort
    0.10
     Fort
    0.10
     Battery
    0.09
    Fort
    0.09
     defensive
    0.09
    Battery
    0.09
     bunk
    0.09
     defenses
    0.09
    Activations Density 0.017%

    No Known Activations