INDEX

Explanations

substantial abbreviations and names that indicate roles or positions within organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

\grid

-0.17

//{{

-0.16

Ð¸ÑģÐ»Ð¾Ð²

-0.16

ãĥ©ãĥĥãĤ¯

-0.15

prox

-0.15

gree

-0.15

åĲįçĦ¡ãģĹ

-0.15

#af

-0.15

#aa

-0.15

.lu

-0.14

POSITIVE LOGITS

 caster

0.14

ocrine

0.14

ãģ£ãģ¨

0.14

 cata

0.14

0.13

fy

0.13

 Mezi

0.13

aller

0.13

 ÑģÑĤÐ¾ÑĢ

0.13

Ã³l

0.13

Activations Density 0.971%

substantial abbreviations and names that indicate roles or positions within organizations

No Comments

No Known Activations