INDEX

Explanations

references to National Insurance and 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 @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ries

-0.14

ÙģÙĪ

-0.14

alace

-0.14

hti

-0.14

 pierced

-0.14

CTSTR

-0.14

Ø±ÙģØ©

-0.14

Ä±nca

-0.14

gew

-0.13

_unicode

-0.13

POSITIVE LOGITS

amo

0.16

anj

0.15

Ã©g

0.15

ylland

0.15

 McMaster

0.14

anja

0.14

arena

0.14

.UIManager

0.14

exp

0.13

Activations Density 0.023%

references to National Insurance and related terms

No Comments

No Known Activations