INDEX

Explanations

phrases related to significant risks 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 @ 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

rias

-0.16

 ÙħÛĮÙĦ

-0.15

Own

-0.15

halt

-0.15

uben

-0.14

CreatedBy

-0.14

regnum

-0.14

alez

-0.14

aÅ¼

-0.14

enta

-0.13

POSITIVE LOGITS

enna

0.15

áº¡i

0.15

opes

0.15

anni

0.15

Av

0.14

ope

0.14

.opens

0.13

ç¬ĳ

0.13

av

0.13

Av

0.13

Activations Density 1.322%

phrases related to significant risks and achievements

No Comments

No Known Activations