INDEX

Explanations

numerical values, particularly the number eight

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ëį°

-0.23

ORIZONTAL

-0.16

ait

-0.15

st

-0.15

 Liberties

-0.14

tra

-0.14

ungan

-0.14

tons

-0.14

set

-0.14

 ÑģÐ¾Ð±Ð¾Ð¹

-0.14

POSITIVE LOGITS

eenth

0.39

een

0.35

../../

0.17

th

0.17

brtc

0.16

bern

0.16

ï¸ı

0.15

iris

0.15

à¸°

0.15

sburg

0.15

Activations Density 0.250%

numerical values, particularly the number eight

No Comments

No Known Activations