© 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. 77360
    Prev
    Next
    INDEX
    Explanations

    phrases and variations related to the action of creating or constructing something

    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
    baum
    -0.07
     meanwhile
    -0.06
    Ñĥг
    -0.06
     Reach
    -0.06
    .ms
    -0.06
    asca
    -0.06
    ì²ĺ
    -0.05
     Paths
    -0.05
    sta
    -0.05
    ById
    -0.05
    POSITIVE LOGITS
    íģ¼
    0.07
    νοÏį
    0.07
    ovnÃŃ
    0.07
    ذا
    0.07
    specs
    0.07
    ancode
    0.07
    Interop
    0.06
    vÄĽt
    0.06
    ires
    0.06
     Jenkins
    0.06
    Activations Density 0.012%

    No Known Activations