INDEX

Explanations

references to specific organizations or groups, particularly in the hospitality and charitable sectors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

yk

-0.19

Å¾iv

-0.17

chant

-0.15

lear

-0.14

CLUDED

-0.14

ohn

-0.14

 )↵↵↵↵↵↵↵↵

-0.14

 Horizontal

-0.14

ëĭ¤ê°Ģ

-0.13

Ø¯ÙĪØ¯

-0.13

POSITIVE LOGITS

rompt

0.18

zÃ¡

0.15

izons

0.15

erty

0.15

ilitation

0.15

 migrationBuilder

0.15

inged

0.15

ighton

0.14

ooter

0.14

Activations Density 0.087%

references to specific organizations or groups, particularly in the hospitality and charitable sectors

No Comments

No Known Activations