Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 84386
    Prev
    Next
    INDEX
    Explanations

    financial metrics and statistical data

    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
    erce
    -0.07
     raw
    -0.06
    rer
    -0.06
    atur
    -0.06
    uslim
    -0.06
     Mo
    -0.06
     uptime
    -0.06
     extract
    -0.05
    asha
    -0.05
    ogan
    -0.05
    POSITIVE LOGITS
    ếp
    0.07
    Fcn
    0.07
    ailability
    0.07
    å·»
    0.07
    Ùħت
    0.07
    à¹Įà¹Ģà¸Ļ
    0.06
    .RequestBody
    0.06
    defgroup
    0.06
     EXEMPLARY
    0.06
    cé
    0.06
    Activations Density 0.003%

    No Known Activations