INDEX

Explanations

expressions of comparison and contrast between different subjects or ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 sharp

-0.22

 weakest

-0.15

 shar

-0.15

 sharpen

-0.15

 sharply

-0.14

 anybody

-0.14

 happiest

-0.14

sharp

-0.14

 quickest

-0.14

Sharp

-0.13

POSITIVE LOGITS

 more

0.75

æĽ´

0.63

more

0.57

æĽ´åĬł

0.57

 better

0.56

 lebih

0.55

 æĽ´

0.54

 daha

0.53

 greater

0.52

 less

0.51

Activations Density 3.034%

expressions of comparison and contrast between different subjects or ideas

No Comments

No Known Activations