© 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. 57262
    Prev
    Next
    INDEX
    Explanations

    phrases that begin with "as" in a variety of contexts

    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
    ãĤ¹ãĤ¯
    -0.07
    atos
    -0.06
    orda
    -0.06
    continent
    -0.06
    otope
    -0.06
    оÑĩ
    -0.06
    ÑĢÑıд
    -0.06
    .guid
    -0.06
    overs
    -0.06
    etter
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.07
    esub
    0.07
    ewire
    0.07
    erten
    0.07
    endor
    0.07
    اÙĬÙĦ
    0.07
     thẳng
    0.07
    ëłĪìĬ¤
    0.06
    aley
    0.06
     же
    0.06
    Activations Density 0.035%

    No Known Activations