INDEX

Explanations

references to organizations and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 Pacific

-0.14

.cgi

-0.14

tok

-0.14

èĪĪ

-0.14

Roc

-0.13

 divers

-0.13

 DÃ¼n

-0.13

 empty

-0.13

éĤ¦

-0.13

^K

-0.13

POSITIVE LOGITS

ama

0.18

ounty

0.16

DITION

0.15

æĹıèĩªæ²»

0.15

ords

0.14

ilst

0.14

unate

0.13

 Slug

0.13

 Bris

0.13

-toggler

0.13

Activations Density 0.354%

references to organizations and locations

No Comments

No Known Activations