INDEX

Explanations

concepts related to concern, loss, and uncertainty in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 where

-0.16

-0.15

cl

-0.15

Hib

-0.15

ro

-0.15

sv

-0.15

 Mach

-0.14

ure

-0.14

posix

-0.14

 fore

-0.14

POSITIVE LOGITS

ableView

0.16

","+

0.15

done

0.15

ezier

0.15

ignKey

0.15

iaux

0.15

ertino

0.15

ofire

0.15

YYS

0.15

ckett

0.15

Activations Density 0.312%

concepts related to concern, loss, and uncertainty in various contexts

No Comments

No Known Activations