INDEX

Explanations

words related to obstacles or limitations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

anio

-0.17

undler

-0.16

ÑĥÐºÐ¸

-0.14

 fuels

-0.14

Ø¯ÛĮØ¯

-0.14

 lá»ĩnh

-0.14

 Extreme

-0.13

.wp

-0.13

.Sequence

-0.13

xbb

-0.13

POSITIVE LOGITS

ãĥ³ãĤ¯

0.18

edReader

0.17

edImage

0.17

reuse

0.15

imest

0.15

 ìĤ¬íķŃ

0.15

idades

0.14

olls

0.14

agu

0.14

Activations Density 0.016%

words related to obstacles or limitations

No Comments

No Known Activations