© 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. 17-LLAMASCOPE-RES-131K
    6. 106389
    Prev
    Next
    INDEX
    Explanations

    phrases related to staying current or informed

    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
    marvin
    -0.07
    anka
    -0.07
    ady
    -0.07
    hetto
    -0.07
    ominator
    -0.07
    artment
    -0.07
    anza
    -0.07
    (CultureInfo
    -0.07
    esty
    -0.06
    浩
    -0.06
    POSITIVE LOGITS
    LEGRO
    0.06
    -to
    0.06
    olle
    0.06
    iq
    0.06
    638
    0.06
    ToDate
    0.05
    licative
    0.05
     FIL
    0.05
    HostException
    0.05
    vie
    0.05
    Activations Density 0.003%

    No Known Activations