INDEX

Explanations

terms related to emergence and new developments

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

izz

-0.15

TF

-0.14

ven

-0.14

 Father

-0.14

çķ

-0.14

mee

-0.14

ÎµÏĨ

-0.14

 Vert

-0.14

arra

-0.14

ittings

-0.13

POSITIVE LOGITS

0.14

 from

0.14

-from

0.14

ropol

0.14

ÏĦÎ¹Î½

0.14

 dáº§n

0.13

±ä¹Ĳ

0.13

ë°Ķ

0.13

uder

0.13

Activations Density 0.016%

terms related to emergence and new developments

No Comments

No Known Activations