INDEX

Explanations

words related to instructions or actions involving change and decision-making

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 inst

-0.17

inst

-0.16

ntp

-0.15

_PD

-0.15

Î±Ïģ

-0.15

endale

-0.14

Ø±Ø§ÙĨÙĩ

-0.14

ymax

-0.14

ĥ

-0.14

usp

-0.14

POSITIVE LOGITS

science

0.18

Pending

0.16

 Motion

0.15

bere

0.14

itespace

0.14

eyer

0.14

 library

0.14

scientific

0.14

Convention

0.14

 conventions

0.13

Activations Density 0.008%

words related to instructions or actions involving change and decision-making

No Comments

No Known Activations