© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 23-LLAMASCOPE-RES-32K
    11. 21848
    Prev
    Next
    INDEX
    Explanations

    instances of phrases related to leveraging or taking advantage of opportunities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ammen
    -0.18
    ossa
    -0.15
    iaux
    -0.15
    orio
    -0.15
    еко
    -0.14
    nez
    -0.14
    iban
    -0.14
    áºł
    -0.14
    orning
    -0.13
    anto
    -0.13
    POSITIVE LOGITS
     opportunities
    0.40
     opportunity
    0.36
     Opportunities
    0.33
     Opportunity
    0.28
     oportun
    0.28
     available
    0.26
     resources
    0.25
     existing
    0.25
     advantages
    0.25
     Available
    0.23
    Activations Density 0.117%

    No Known Activations