INDEX

Explanations

concepts related to communication and support among people 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 @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

Ã©tÃ©

-0.16

uten

-0.15

undy

-0.15

 Tempo

-0.15

apore

-0.15

itia

-0.15

Nob

-0.14

ichni

-0.14

ivil

-0.14

setWidth

-0.14

POSITIVE LOGITS

imat

0.17

ãģİ

0.16

HOOK

0.15

ActionButton

0.14

 Damen

0.14

Muj

0.14

-hooks

0.13

Mud

0.13

ISC

0.13

getic

0.13

Activations Density 0.874%

concepts related to communication and support among people in various contexts

No Comments

No Known Activations