© 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. 126764
    Prev
    Next
    INDEX
    Explanations

    elements indicating structural organization or classification in 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
    rrha
    -0.06
    ữu
    -0.06
    isans
    -0.06
    echa
    -0.06
    ivers
    -0.06
    ion
    -0.05
     Became
    -0.05
     etc
    -0.05
     Brennan
    -0.05
    bond
    -0.05
    POSITIVE LOGITS
    ÏĮÏģ
    0.08
    ãģ¾ãģļ
    0.07
    Danny
    0.07
    oor
    0.07
    ãģĬãĤĬ
    0.07
    ÙĮ
    0.07
    ä¸Ķ
    0.07
    oÄŁ
    0.07
    summ
    0.07
     ìŀĪê³ł
    0.07
    Activations Density 0.054%

    No Known Activations