© 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. 94024
    Prev
    Next
    INDEX
    Explanations

    terms related to algorithmic processes and functions within programming 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
    licative
    -0.07
    èħ
    -0.07
     Barcl
    -0.07
    abwe
    -0.07
    usalem
    -0.06
    еко
    -0.06
     chấm
    -0.06
    اصÙĦÙĩ
    -0.06
    .ny
    -0.06
     Mell
    -0.06
    POSITIVE LOGITS
     Removal
    0.07
    akan
    0.07
     removal
    0.07
     اÙĦخط
    0.06
    remove
    0.06
     Crane
    0.06
    lek
    0.06
     merges
    0.06
     пÑĢоÑģ
    0.06
     initially
    0.06
    Activations Density 0.176%

    No Known Activations