INDEX

Explanations

comparative phrases and expressions that indicate similarity or likeness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 neboÅ¥

-0.16

kah

-0.14

cke

-0.14

stoff

-0.13

igar

-0.13

iffies

-0.13

nÃŃk

-0.13

istringstream

-0.13

uis

-0.13

ynchronously

-0.13

POSITIVE LOGITS

ppard

0.15

ones

0.15

leen

0.15

enger

0.14

merce

0.13

akedown

0.13

 Î±ÏħÏĦÎ¬

0.13

tml

0.13

 denen

0.13

ilestone

0.13

Activations Density 0.060%

comparative phrases and expressions that indicate similarity or likeness

No Comments

No Known Activations