INDEX

Explanations

references to the word "hop" and its variations, particularly in contexts related to movement or action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

 opposite

-0.16

uns

-0.16

antee

-0.16

bre

-0.15

 functional

-0.15

.arg

-0.14

quez

-0.14

Ð¸ÑģÑĮ

-0.14

 past

-0.14

Î²Î¿Î»Î®

-0.14

POSITIVE LOGITS

ÑģÐ¸

0.17

.struts

0.16

gor

0.15

gett

0.15

leg

0.15

oved

0.15

_COMPAT

0.14

PROTO

0.14

shit

0.14

Activations Density 0.011%

references to the word "hop" and its variations, particularly in contexts related to movement or action

No Comments

No Known Activations