INDEX

Explanations

conditional phrases and qualifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 Dank

-0.15

lobals

-0.15

ioxide

-0.14

 ifndef

-0.14

ressed

-0.13

iras

-0.13

argas

-0.13

/packages

-0.13

antor

-0.13

POSITIVE LOGITS

 otherwise

0.25

otherwise

0.21

 jinak

0.19

Otherwise

0.19

 Otherwise

0.18

à¥Ĥà¤Ł

0.18

 OTHERWISE

0.17

coh

0.16

 else

0.15

	else

0.15

Activations Density 0.030%

conditional phrases and qualifiers

No Comments

No Known Activations