INDEX

Explanations

references to company-specific details and agreements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ìŀ¥ìĿĢ

-0.16

 quale

-0.15

à¸¢à¸ĩ

-0.15

ìĥĿëĭĺ

-0.14

ìħĺ

-0.13

ìĿ´ìħĺ

-0.13

 quali

-0.13

ì¹ĺëĬĶ

-0.12

Ã©al

-0.12

ãģĵãģĨ

-0.12

POSITIVE LOGITS

 that

1.31

that

1.09

 THAT

0.96

 That

0.95

That

0.90

	that

0.88

_that

0.86

 ráº±ng

0.84

 ÑĩÑĤÐ¾

0.76

 bahwa

0.74

Activations Density 1.201%

references to company-specific details and agreements

No Comments

No Known Activations

references to company-specific details and agreements

No Comments

No Known Activations