INDEX

Explanations

markup or formatting syntax in code

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

 August

-0.20

 listed

-0.17

 late

-0.17

 eight

-0.17

ä»ĭ

-0.17

-Aug

-0.17

ł

-0.16

Aug

-0.16

åħ«

-0.16

 eighth

-0.16

POSITIVE LOGITS

0.56

ÂłÂłÂłÂłÂłÂłÂł

0.30

0.22

ãĢĢãĢĢãĢĢ

0.21

0.20

--------↵↵

0.19

ãĢĢãĢĢ ãĢĢ

0.19

0.18

.......

0.18

========

0.17

Activations Density 0.038%

markup or formatting syntax in code

No Comments

No Known Activations