© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 18-LLAMASCOPE-RES-32K
    11. 16273
    Prev
    Next
    INDEX
    Explanations

    references to governmental bodies and agencies

    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
     Rajasthan
    -0.18
    spiel
    -0.15
    (REG
    -0.15
    izona
    -0.15
    åĨ
    -0.15
    iteli
    -0.15
     Albuquerque
    -0.15
     Manitoba
    -0.15
     Sind
    -0.15
     Idaho
    -0.15
    POSITIVE LOGITS
     Maryland
    0.56
     Baltimore
    0.54
    altimore
    0.40
     Ches
    0.40
     Orioles
    0.38
     Md
    0.33
     Balt
    0.28
    Mary
    0.28
     MD
    0.27
    Md
    0.27
    Activations Density 0.182%

    No Known Activations