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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 27-LLAMASCOPE-RES-32K
    6. 52
    Prev
    Next
    INDEX
    Explanations

    elements related to the historical and cultural significance of wine in regions of French-speaking Switzerland

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    airobi
    -0.15
    stin
    -0.15
    aku
    -0.14
    caff
    -0.14
    ellular
    -0.14
    066
    -0.13
     Fault
    -0.13
     èª
    -0.13
    ç¦
    -0.13
    ÃŃtulo
    -0.13
    POSITIVE LOGITS
     Norm
    0.47
     Prov
    0.40
    Norm
    0.39
     Brittany
    0.37
    Prov
    0.35
     Bret
    0.34
     Als
    0.34
     Burg
    0.33
     Lomb
    0.32
     Champagne
    0.31
    Activations Density 0.200%

    No Known Activations