INDEX

Explanations

references to posters or poster-related concepts

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

men

-0.16

emen

-0.16

sc

-0.15

/goto

-0.15

reich

-0.15

sg

-0.15

vil

-0.15

son

-0.14

RuntimeObject

-0.14

ìĶ

-0.14

POSITIVE LOGITS

ised

0.18

ifu

0.17

ized

0.17

ry

0.17

ibbon

0.17

izes

0.16

iface

0.16

iff

0.15

anguages

0.14

efd

0.14

Activations Density 0.049%

references to posters or poster-related concepts

No Comments

No Known Activations