INDEX

Explanations

phrases that imply a sense of authority or official statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

Mrs

-0.14

Mrs

-0.14

 "...

-0.14

 gauss

-0.13

ÙĬÙĩ

-0.13

tons

-0.13

Ã§o

-0.13

.scalablytyped

-0.13

 ÐĿÐ°Ð³

-0.13

vs

-0.13

POSITIVE LOGITS

ohn

0.16

usch

0.15

Å¾dy

0.14

é¦

0.14

Stencil

0.13

urname

0.13

odiac

0.13

apo

0.13

reib

0.13

ought

0.13

Activations Density 0.000%

phrases that imply a sense of authority or official statements

No Comments

No Known Activations