INDEX

Explanations

references to character types and encodings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

Ú¯Ø§Ùĩ

-0.17

Ú¯Ø§ÙĩÛĮ

-0.16

elight

-0.15

haps

-0.15

bery

-0.14

 Editorial

-0.14

erner

-0.14

uden

-0.14

oman

-0.14

arel

-0.14

POSITIVE LOGITS

ized

0.17

pell

0.15

peria

0.15

uegos

0.15

ottes

0.15

ually

0.15

ãĥ³ãĥĨãĤ£

0.14

ped

0.14

ystery

0.14

Ã¼b

0.14

Activations Density 0.029%

references to character types and encodings

No Comments

No Known Activations