INDEX

Explanations

instances of the ellipsis or "…" used for punctuation or to indicate omitted information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

odore

-0.34

xiety

-0.18

atre

-0.17

adays

-0.16

/respond

-0.16

oka

-0.16

anan

-0.15

structor

-0.15

lung

-0.15

FTA

-0.15

POSITIVE LOGITS

é¡µéĿ¢åŃĺæ¡£å¤ĩä»½

0.24

 latter

0.21

YC

0.16

YD

0.16

omer

0.15

Ø¨Ø§Ø±

0.15

phans

0.15

eneg

0.15

ÐĲÑĢÑħÑĸÐ²Ð¾Ð²Ð°Ð½Ð¾

0.14

egral

0.14

Activations Density 0.038%

instances of the ellipsis or "…" used for punctuation or to indicate omitted information

No Comments

No Known Activations