© 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. 78057
    Prev
    Next
    INDEX
    Explanations

    the verb "led" indicating direction or guidance in a narrative context

    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
    .Syntax
    -0.07
    ighbor
    -0.07
     theater
    -0.07
    oxel
    -0.07
    ofire
    -0.07
    neighbor
    -0.07
    ±
    -0.07
    ekli
    -0.07
     neighborhood
    -0.06
     rumor
    -0.06
    POSITIVE LOGITS
    amo
    0.07
    ahr
    0.06
    ider
    0.06
    untime
    0.06
    AXB
    0.06
    hay
    0.06
     Animalia
    0.06
    bern
    0.06
     Mile
    0.06
    iming
    0.06
    Activations Density 0.000%

    No Known Activations