INDEX

Explanations

expressions of careful or intentional 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 @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ocab

-0.17

orrect

-0.16

azo

-0.15

-0.14

 bapt

-0.14

 welt

-0.13

à¥įà¤µà¤°

-0.13

suz

-0.13

 suspected

-0.13

 possible

-0.13

POSITIVE LOGITS

orda

0.14

ovnÄĽ

0.14

ogne

0.14

.Framework

0.14

æ¤

0.14

ropp

0.13

deniz

0.13

PLAIN

0.13

SEA

0.13

Activations Density 0.059%

expressions of careful or intentional decision-making

No Comments

No Known Activations