INDEX

Explanations

references to performance and implementation in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

loor

-0.14

ello

-0.14

geber

-0.14

uhl

-0.14

Ã³ln

-0.14

Å¡el

-0.14

FD

-0.13

gard

-0.13

raq

-0.13

 gest

-0.13

POSITIVE LOGITS

jev

0.17

heim

0.16

ubi

0.15

 otherwise

0.14

 kÃ¥

0.14

.mybatisplus

0.14

Ð½Ð°Ð¼

0.14

 ExecutionContext

0.14

oho

0.14

íĨłíĨł

0.13

Activations Density 0.750%

references to performance and implementation in various contexts

No Comments

No Known Activations