INDEX

Explanations

phrases that express intentions or actions starting with "to."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 Disc

-0.16

 discs

-0.16

-0.15

 disc

-0.15

 discourse

-0.15

#ac

-0.14

Ã¢l

-0.14

eo

-0.13

 discard

-0.13

patches

-0.13

POSITIVE LOGITS

ies

0.17

IES

0.15

ysl

0.15

NotSupportedException

0.14

sehen

0.14

à¤¹à¤²

0.14

Ø´Ø¨

0.14

vvm

0.14

//{{

0.14

Å½

0.14

Activations Density 0.025%

phrases that express intentions or actions starting with "to."

No Comments

No Known Activations