INDEX

Explanations

expressions related to adaptation and getting accustomed to new situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ollen

-0.20

erot

-0.17

ksam

-0.16

erse

-0.15

itecture

-0.15

hma

-0.14

resse

-0.14

allery

-0.14

ix

-0.14

olics

-0.14

POSITIVE LOGITS

 habit

0.16

habit

0.15

orro

0.15

 habits

0.15

earer

0.15

ibi

0.14

.Italic

0.14

ayne

0.14

 Habit

0.14

ÑģÐ¸

0.14

Activations Density 0.033%

expressions related to adaptation and getting accustomed to new situations

No Comments

No Known Activations