© 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. 5-LLAMASCOPE-RES-131K
    11. 125955
    Prev
    Next
    INDEX
    Explanations

    variable assignments in programming or markup languages

    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
     ฿
    -0.07
    fy
    -0.07
    apon
    -0.07
    ettel
    -0.06
    iom
    -0.06
    andid
    -0.06
    pest
    -0.06
    ç´¹
    -0.06
    XS
    -0.06
    cob
    -0.06
    POSITIVE LOGITS
     Lamp
    0.08
    él
    0.06
     NodeType
    0.06
     ApplicationException
    0.06
    hatt
    0.06
     weekly
    0.06
    ÑĤаб
    0.06
     Haut
    0.06
    ubl
    0.06
    çĶº
    0.06
    Activations Density 0.000%

    No Known Activations