© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126594
    Prev
    Next
    INDEX
    Explanations

    references to a specific rating or classification system

    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
     
    -0.08
     however
    -0.06
    ume
    -0.06
     (
    -0.06
    ,
    -0.06
    .
    -0.06
    teenth
    -0.06
    ijken
    -0.05
    za
    -0.05
    ete
    -0.05
    POSITIVE LOGITS
     Animalia
    0.08
    abama
    0.07
    irst
    0.07
    олеÑĤ
    0.07
    senal
    0.07
    _LCD
    0.07
     mastur
    0.07
    å¢
    0.07
    eczy
    0.07
    _Framework
    0.07
    Activations Density 0.001%

    No Known Activations