INDEX

Explanations

elements related to programming and technical features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

-0.15

chr

-0.15

oser

-0.14

 Wing

-0.14

 Rudd

-0.14

obic

-0.14

 cape

-0.14

Ð³Ð¾

-0.14

»

-0.13

Haw

-0.13

POSITIVE LOGITS

 beyond

0.17

esi

0.16

eyond

0.16

ä½¿

0.15

 compared

0.15

ukkit

0.15

 besides

0.15

otre

0.14

uez

0.14

 than

0.14

Activations Density 0.353%

elements related to programming and technical features

No Comments

No Known Activations