© 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. 18-LLAMASCOPE-RES-32K
    6. 29058
    Prev
    Next
    INDEX
    Explanations

    references to spatial availability and accessibility in various regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bend
    -0.15
     Industry
    -0.15
     Pam
    -0.15
    Industry
    -0.14
    Benchmark
    -0.14
    uron
    -0.14
     Benchmark
    -0.14
    anchor
    -0.13
     bench
    -0.13
    ÙıÙĪØ§
    -0.13
    POSITIVE LOGITS
     countries
    0.20
     territories
    0.18
     regions
    0.16
     Countries
    0.16
    -CN
    0.16
     اÙĦÙħÙħÙĦÙĥØ©
    0.16
     Australia
    0.15
     UK
    0.15
    /format
    0.15
    countries
    0.15
    Activations Density 0.136%

    No Known Activations