INDEX

Explanations

expressions of inquiry or questions

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

/layouts

-0.15

deaux

-0.15

rellas

-0.14

leme

-0.14

ãĤ

-0.14

èĲ½ãģ¡

-0.14

ÙĨØ©

-0.14

izzo

-0.13

_parms

-0.13

POSITIVE LOGITS

upal

0.18

abbo

0.16

 âĨĴ↵↵

0.15

erta

0.15

AGMA

0.15

airo

0.14

 Ð´ÐµÐ½

0.14

Urb

0.13

REC

0.13

actic

0.13

Activations Density 0.028%

expressions of inquiry or questions

No Comments

No Known Activations