INDEX

Explanations

abbreviations or acronyms related to government and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

rig

-0.19

rone

-0.19

odb

-0.18

angelo

-0.18

isses

-0.17

rung

-0.17

ettle

-0.17

ett

-0.16

ring

-0.16

riger

-0.15

POSITIVE LOGITS

ourmet

0.19

lat

0.16

ested

0.16

OLF

0.15

hee

0.15

azi

0.15

reetings

0.15

Ã»t

0.15

KV

0.15

heard

0.14

Activations Density 0.041%

abbreviations or acronyms related to government and organizations

No Comments

No Known Activations