INDEX

Explanations

variations of the suffix "ers," indicating the presence of agents or doers in the text

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

uddle

-0.16

.nlm

-0.16

 Replies

-0.16

 sockfd

-0.15

gien

-0.14

ousel

-0.14

odÃŃ

-0.14

ogle

-0.14

ocities

-0.14

owski

-0.14

POSITIVE LOGITS

etro

0.15

ACE

0.15

ACE

0.15

ipher

0.15

Ð½ÑĸÐ²

0.14

innie

0.14

 Renderer

0.13

 waters

0.13

asa

0.13

atÃ³

0.13

Activations Density 0.068%

variations of the suffix "ers," indicating the presence of agents or doers in the text

No Comments

No Known Activations