INDEX

Explanations

instances of significant events or elements related to crime or legal issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

kate

-0.16

gv

-0.15

elop

-0.14

uros

-0.14

anj

-0.14

&o

-0.14

akk

-0.14

 dual

-0.14

ëī´ìĬ¤

-0.14

eken

-0.13

POSITIVE LOGITS

erialize

0.15

contro

0.15

robe

0.15

lege

0.15

å¾®è½¯éĽħé»ĳ

0.15

uvo

0.14

oyer

0.14

ãĥ¯ãĤ¤ãĥĪ

0.14

cone

0.14

resher

0.13

Activations Density 0.254%

instances of significant events or elements related to crime or legal issues

No Comments

No Known Activations