INDEX

Explanations

descriptions of thinness or slimness in characters or objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

-0.16

zon

-0.15

kla

-0.14

 paramMap

-0.14

æ³¥

-0.14

igli

-0.14

antal

-0.14

ovnÄĽ

-0.14

gel

-0.14

iard

-0.14

POSITIVE LOGITS

ning

0.18

ened

0.18

est

0.17

ore

0.17

ness

0.16

ening

0.16

unb

0.16

NING

0.15

uggy

0.15

xAC

0.15

Activations Density 0.033%

descriptions of thinness or slimness in characters or objects

No Comments

No Known Activations