INDEX

Explanations

references to the Pandas library and its functions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

tingham

-0.17

rench

-0.16

wo

-0.15

eting

-0.14

idding

-0.14

udded

-0.14

 dripping

-0.14

lated

-0.14

noop

-0.14

att

-0.14

POSITIVE LOGITS

 VerfÃ¼g

0.15

(~(

0.14

OMEM

0.14

bsub

0.14

memory

0.14

.gdx

0.14

 Gupta

0.13

PageRoute

0.13

 Sunder

0.13

_NONNULL

0.13

Activations Density 0.014%

references to the Pandas library and its functions

No Known Activations