INDEX

Explanations

titles, names, and significant identifiers within a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

wart

-0.18

ecut

-0.15

zier

-0.15

.mit

-0.15

Ø²

-0.15

æ´ª

-0.14

stab

-0.14

oine

-0.14

Å¡t

-0.13

ÑĢÐ¾Ð³

-0.13

POSITIVE LOGITS

IFS

0.15

 Networking

0.13

Correction

0.13

ØªØ±ÛĮ

0.13

 pstmt

0.13

æ±º

0.13

ents

0.13

(nr

0.12

ideo

0.12

 ãĤ¸ãĥ£

0.12

Activations Density 0.438%

titles, names, and significant identifiers within a text

No Comments

No Known Activations