INDEX

Explanations

phonetic similarities and pronunciation examples across different languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

èĥĨ

-0.16

selectAll

-0.14

con

-0.14

 sort

-0.14

 puis

-0.14

ried

-0.14

@qq

-0.14

rig

-0.14

lsru

-0.13

innie

-0.13

POSITIVE LOGITS

olean

0.15

 åł

0.14

 resil

0.14

ecta

0.13

 safeg

0.13

iaz

0.13

KeyName

0.13

anh

0.13

 ØŃØ°

0.13

adder

0.12

Activations Density 0.025%

phonetic similarities and pronunciation examples across different languages

No Comments

No Known Activations