INDEX

Explanations

words related to attempts or efforts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

emente

-0.16

olib

-0.16

ater

-0.15

 kond

-0.14

allow

-0.14

elles

-0.14

auen

-0.14

ritch

-0.13

 Ð¾Ð±ÑıÐ·Ð°Ð½

-0.13

áº¬

-0.13

POSITIVE LOGITS

 desperately

0.29

 unsuccessfully

0.28

to

0.27

 hard

0.27

 vain

0.26

 harder

0.24

hard

0.23

val

0.23

 desper

0.23

 hardest

0.22

Activations Density 0.050%

words related to attempts or efforts

No Comments

No Known Activations