INDEX

Explanations

references to data tables or figures in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

-0.18

ilee

-0.16

 simd

-0.16

Ã¢m

-0.15

asks

-0.14

acob

-0.14

æļ®

-0.14

owan

-0.14

POSITIVE LOGITS

shed

0.15

oha

0.15

atial

0.14

Î´Î·

0.14

igm

0.14

_formatter

0.14

.dd

0.14

iac

0.14

olut

0.14

.DataType

0.13

Activations Density 0.034%

references to data tables or figures in scientific contexts

No Comments

No Known Activations