INDEX

Explanations

phrases indicating uncertainty or the need for future evaluation

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

sez

-0.15

.SingleOrDefault

-0.15

à¤¾à¤¯à¤ķ

-0.14

ugs

-0.14

.authorization

-0.14

 ÄĳÃ´i

-0.14

ÃĹ↵↵

-0.13

neo

-0.13

askell

-0.13

Ã©g

-0.13

POSITIVE LOGITS

 whether

0.17

ê²Į

0.16

angling

0.14

XL

0.14

_VOID

0.14

Ø¥

0.13

ivy

0.13

æĺ¯åĲ¦

0.13

odge

0.13

Vi

0.13

Activations Density 0.035%

phrases indicating uncertainty or the need for future evaluation

No Comments

No Known Activations