© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 94351
    Prev
    Next
    INDEX
    Explanations

    phrases indicating references or citations related to various 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
    .DropDown
    -0.10
    ì§ĢëıĦ
    -0.09
    ãĥģãĥ¥
    -0.09
    ÑĪев
    -0.09
    .Contract
    -0.09
    .Dictionary
    -0.08
    .accounts
    -0.08
     prez
    -0.08
    âĻ¡
    -0.08
    大人
    -0.08
    POSITIVE LOGITS
    /how
    0.08
    utterstock
    0.06
    aye
    0.06
     seedu
    0.06
    aget
    0.06
     reuseIdentifier
    0.05
    /from
    0.05
    stantiateViewController
    0.05
    UNDLE
    0.05
    ollen
    0.05
    Activations Density 0.146%

    No Known Activations