INDEX

Explanations

references to specific companies and their market activities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 dÄ±ÅŁÄ±nda

-0.15

 totiÅ¾

-0.14

 notamment

-0.13

à¸Ńà¸Ħ

-0.13

arest

-0.13

foy

-0.13

 ademÃ¡s

-0.13

ÏĥÏħ

-0.13

arel

-0.12

 besonders

-0.12

POSITIVE LOGITS

 similarly

1.14

 likewise

0.87

 equally

0.83

 Similarly

0.81

 similar

0.80

Similarly

0.77

 ebenfalls

0.75

similar

0.70

 Likewise

0.67

imilar

0.61

Activations Density 1.168%

references to specific companies and their market activities

No Comments

No Known Activations