INDEX

Explanations

words indicating diversity and abundance in quantities or variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

-0.16

-0.15

sod

-0.14

owa

-0.14

à¥Ģà¤Ľ

-0.14

shed

-0.13

rium

-0.13

umu

-0.13

POSITIVE LOGITS

Ð°Ð½Ð¸ÑĨ

0.14

fos

0.14

uden

0.14

Ð¢Ðŀ

0.14

wish

0.14

UNCT

0.14

Ø³Ø§ÙĨÛĮ

0.14

ElementException

0.14

velle

0.14

abad

0.13

Activations Density 0.159%

words indicating diversity and abundance in quantities or variations

No Comments

No Known Activations