INDEX

Explanations

regulatory and compliance-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

mares

-0.16

_armor

-0.15

ÅĻenÃŃ

-0.15

 Shore

-0.14

ADF

-0.14

_intr

-0.14

Gut

-0.14

 Dirty

-0.13

textTheme

-0.13

 dÃ©t

-0.13

POSITIVE LOGITS

brtc

0.16

wan

0.15

 harc

0.15

alara

0.15

amon

0.15

 butterfly

0.15

apol

0.14

esson

0.14

-transitional

0.14

Activations Density 0.070%

regulatory and compliance-related terms

No Comments

No Known Activations