© 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. 125818
    Prev
    Next
    INDEX
    Explanations

    mentions of authorship or attribution in the text

    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
    anine
    -0.07
    ary
    -0.07
    EDIA
    -0.06
    lan
    -0.06
    orf
    -0.06
    iece
    -0.06
     shr
    -0.06
     Talk
    -0.06
     responseBody
    -0.06
    ürger
    -0.06
    POSITIVE LOGITS
    éru
    0.07
    divid
    0.07
    .ast
    0.07
    оÑİ
    0.07
    .rm
    0.07
    uml
    0.06
    ssc
    0.06
    tti
    0.06
    hlas
    0.06
    illisecond
    0.06
    Activations Density 0.003%

    No Known Activations