INDEX

Explanations

historical references and significant dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

emark

-0.16

pam

-0.15

 DateFormatter

-0.14

wen

-0.14

ighth

-0.14

ograd

-0.14

IEW

-0.14

steller

-0.14

itti

-0.14

-0.13

POSITIVE LOGITS

Latch

0.16

acle

0.15

tail

0.15

 Benton

0.14

ylie

0.13

ACP

0.13

 giáº£

0.13

suy

0.13

alleries

0.13

Activations Density 0.072%

historical references and significant dates

No Comments

No Known Activations