INDEX

Explanations

statements made by individuals in the context of discussions or reports on social issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

raya

-0.17

uten

-0.16

utt

-0.15

Ð¾ÐºÑĥ

-0.15

missive

-0.15

rud

-0.15

leon

-0.15

 voks

-0.15

vell

-0.15

gue

-0.14

POSITIVE LOGITS

.glide

0.14

ark

0.14

Rh

0.13

 standards

0.13

instein

0.13

 ÑģÐºÐ¾ÑĢ

0.13

akers

0.13

 prince

0.13

 rÄĥng

0.12

reate

0.12

Activations Density 0.126%

statements made by individuals in the context of discussions or reports on social issues

No Comments

No Known Activations