INDEX

Explanations

phrases indicating a sense of struggle or difficulty

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

legen

-0.16

isle

-0.16

="{!!

-0.14

classname

-0.14

 Lions

-0.14

unks

-0.14

lec

-0.14

uled

-0.14

éħį

-0.14

kening

-0.13

POSITIVE LOGITS

ÑģÑĤÑĮ

0.17

ouz

0.16

 possession

0.15

pendicular

0.15

 Chan

0.14

uppe

0.14

à¸¸à¸Ľ

0.14

ite

0.14

ols

0.13

Had

0.13

Activations Density 0.109%

phrases indicating a sense of struggle or difficulty

No Comments

No Known Activations