© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4195
    Prev
    Next
    INDEX
    Explanations

    instances of the word "pave" or its variations, indicating a focus on the concept of laying groundwork or establishing paths

    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
    orf
    -0.08
    λεÏį
    -0.07
    ERRU
    -0.07
    orie
    -0.07
    POR
    -0.07
    uegos
    -0.07
    OTO
    -0.07
    INLINE
    -0.07
    HING
    -0.07
    áºŃt
    -0.07
    POSITIVE LOGITS
     route
    0.08
     path
    0.08
    foot
    0.07
    871
    0.07
    path
    0.07
    ient
    0.07
    asan
    0.07
     groundwork
    0.06
     Bru
    0.06
    ount
    0.06
    Activations Density 0.003%

    No Known Activations