INDEX

Explanations

phrases and terms associated with the word "advanced."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

hots

-0.17

soever

-0.17

NAMESPACE

-0.16

ynes

-0.15

/do

-0.15

:NSLocalizedString

-0.15

ynch

-0.14

/watch

-0.14

lian

-0.14

acman

-0.14

POSITIVE LOGITS

-stage

0.21

-placement

0.20

 degrees

0.20

 notice

0.20

antages

0.19

 Placement

0.19

-degree

0.19

/exp

0.18

ANCED

0.18

 stages

0.18

Activations Density 0.025%

phrases and terms associated with the word "advanced."

No Comments

No Known Activations