INDEX

Explanations

numerical values or parameters in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

-0.18

-0.17

 Five

-0.17

_five

-0.16

 äºĶ

-0.16

ives

-0.16

 Fifth

-0.16

/******/

-0.16

POSITIVE LOGITS

0.29

0.26

 seventh

0.26

 eighth

0.22

 seven

0.22

 Seventh

0.20

VII

0.19

 eight

0.19

à¥Ń

0.18

 July

0.18

Activations Density 0.076%

numerical values or parameters in various contexts

No Comments

No Known Activations