INDEX

Explanations

ellipses or pauses in written text

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

¢°

-0.15

.grp

-0.15

hor

-0.14

leh

-0.14

wie

-0.14

rame

-0.13

acin

-0.13

áºŃt

-0.13

 ÐŁÐ¾Ð¿

-0.13

ays

-0.13

POSITIVE LOGITS

uguay

0.17

 Elli

0.15

.scalablytyped

0.15

olute

0.14

covered

0.14

 dá»¥c

0.14

Ã¦kke

0.13

radi

0.13

NONE

0.13

 carve

0.13

Activations Density 0.006%

ellipses or pauses in written text

No Comments

No Known Activations