INDEX

Explanations

references to visual elements or visual programming concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ÑħÑĥ

-0.17

Ã¡li

-0.15

Ø±Ø¶

-0.15

Ø©

-0.14

à¤°à¤£

-0.14

ãĥİ

-0.14

McC

-0.14

zier

-0.14

kup

-0.14

Ð¾ÑĢÐ¾Ð¼

-0.14

POSITIVE LOGITS

_B

0.17

-B

0.16

²

0.15

Ð»Ð°Ð³Ð°

0.15

Lng

0.15

'B

0.15

-b

0.15

 Ðĳ

0.14

ssi

0.14

’Brien

0.14

Activations Density 0.059%

references to visual elements or visual programming concepts

No Comments

No Known Activations