INDEX

Explanations

phrases that indicate social interactions or relationships

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

arem

-0.14

.construct

-0.14

Ð°Ð¶

-0.14

=log

-0.13

 stalled

-0.13

toc

-0.13

 Denis

-0.13

Ã¡h

-0.13

ÅŁi

-0.13

Î±ÏģÎ¬

-0.13

POSITIVE LOGITS

ieux

0.19

º

0.15

imus

0.15

ouis

0.14

.ManyToMany

0.14

\grid

0.14

onus

0.14

_executor

0.13

ufe

0.13

ibus

0.13

Activations Density 0.824%

phrases that indicate social interactions or relationships

No Comments

No Known Activations