INDEX

Explanations

occurrences of the word "in" and its context within sentences

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

 dropout

-0.16

à¹Ĥà¸Ļ

-0.15

 gradient

-0.15

ritz

-0.14

yen

-0.14

uges

-0.13

ped

-0.13

.sponge

-0.13

 pitchers

-0.13

aqu

-0.13

POSITIVE LOGITS

aho

0.17

elop

0.16

azer

0.15

å«

0.15

Jackson

0.15

ekim

0.14

Î¹Î±Î½

0.14

Uploader

0.14

ailed

0.14

oby

0.14

Activations Density 0.006%

occurrences of the word "in" and its context within sentences

No Comments

No Known Activations