INDEX

Explanations

instances of the word "information" and its related forms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

gradable

-0.16

Helpers

-0.15

Æ°á»¡ng

-0.15

ead

-0.15

host

-0.15

organizations

-0.14

 tá»¥

-0.14

ajar

-0.13

hardt

-0.13

emet

-0.13

POSITIVE LOGITS

quo

0.15

libft

0.14

ckill

0.14

ÑĩÐ°ÑĤ

0.14

aar

0.14

OMET

0.14

iten

0.14

gettext

0.14

Spoiler

0.14

onis

0.14

Activations Density 0.064%

instances of the word "information" and its related forms

No Comments

No Known Activations