INDEX

Explanations

words and phrases related to professional roles and achievements

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

'~/

-0.14

aro

-0.14

 actions

-0.14

pv

-0.14

alborg

-0.13

cia

-0.13

ar

-0.13

 interoper

-0.13

Dit

-0.13

Bou

-0.13

POSITIVE LOGITS

ehir

0.15

imiz

0.15

ConnectionFactory

0.15

æ¬²

0.14

ÐºÐ¾ÑĢÐ¸ÑģÑĤ

0.14

dff

0.14

/Area

0.14

Ī¬

0.14

ansson

0.14

enan

0.14

Activations Density 0.060%

words and phrases related to professional roles and achievements

No Comments

No Known Activations