INDEX

Explanations

references to statistical rates, particularly those indicating low or declining values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ness

-0.17

Ùĩ

-0.17

rt

-0.15

rn

-0.15

iet

-0.15

ry

-0.14

ties

-0.14

ryo

-0.14

imon

-0.14

soft

-0.14

POSITIVE LOGITS

illo

0.17

ully

0.16

.rate

0.16

istrovstvÃŃ

0.16

-rate

0.16

rell

0.15

 Sher

0.15

ascal

0.15

rophic

0.15

-setting

0.15

Activations Density 0.066%

references to statistical rates, particularly those indicating low or declining values

No Comments

No Known Activations