INDEX

Explanations

similarities and repetitiveness in concepts or attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

rud

-0.20

ivec

-0.16

amac

-0.15

 Contrast

-0.14

.getAs

-0.14

ichen

-0.14

jÃŃm

-0.14

 Ã¶yle

-0.14

obili

-0.14

 alone

-0.14

POSITIVE LOGITS

as

0.23

 than

0.21

 ÑĩÑĤÐ¾

0.18

 except

0.18

 quanto

0.17

_than

0.17

wie

0.16

 that

0.16

except

0.16

icker

0.16

Activations Density 0.092%

similarities and repetitiveness in concepts or attributes

No Comments

No Known Activations