INDEX

Explanations

concepts related to treasure and valuable discoveries

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

otope

-0.18

aan

-0.15

unter

-0.15

agn

-0.15

\<^

-0.14

Pla

-0.14

uya

-0.14

aring

-0.14

 walker

-0.14

odium

-0.13

POSITIVE LOGITS

ocations

0.15

azu

0.15

illos

0.15

 INTERRU

0.15

ably

0.14

bih

0.14

odata

0.14

 PureComponent

0.14

ibri

0.14

iben

0.14

Activations Density 0.019%

concepts related to treasure and valuable discoveries

No Comments

No Known Activations