Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 21-LLAMASCOPE-RES-32K
    6. 8528
    Prev
    Next
    INDEX
    Explanations

    references to gas-related topics and energy reform in Mexico

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nunes
    -0.18
    borg
    -0.18
    ossier
    -0.16
    angelo
    -0.15
    occo
    -0.15
    odb
    -0.15
    ipel
    -0.15
    orges
    -0.15
    porto
    -0.15
    encent
    -0.15
    POSITIVE LOGITS
     Mexico
    0.43
     Mexican
    0.40
     México
    0.38
    .mx
    0.37
     mex
    0.36
    Mexico
    0.36
    Mex
    0.35
     MX
    0.34
     Mex
    0.34
     mexico
    0.33
    Activations Density 0.194%

    No Known Activations