INDEX

Explanations

punctuation and conjunctions that indicate ongoing comparisons or contrasts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

stoff

-0.15

ussen

-0.15

plat

-0.15

SO

-0.15

oad

-0.15

elm

-0.14

é¼

-0.14

ecz

-0.14

IFF

-0.14

abcdefghijklmnop

-0.13

POSITIVE LOGITS

 ÐļÐ°Ð±

0.15

issance

0.15

oriously

0.15

$__

0.14

ahr

0.14

ableObject

0.14

 Ð¿Ð¾Ð´Ñģ

0.13

 Jensen

0.13

ancellable

0.13

asic

0.13

Activations Density 0.145%

punctuation and conjunctions that indicate ongoing comparisons or contrasts

No Comments

No Known Activations