INDEX

Explanations

technical terms and functions related to programming or software development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

WithDuration

-0.14

ampa

-0.14

 Ride

-0.14

 ÙħØ¶

-0.14

 RuntimeMethod

-0.14

.Stdout

-0.13

èĭ

-0.13

.ItemStack

-0.13

 Bust

-0.13

 RuntimeObject

-0.13

POSITIVE LOGITS

Seek

0.21

seek

0.20

 seek

0.19

.seek

0.19

SEE

0.18

 Seek

0.18

rew

0.18

 seeking

0.18

 rewind

0.18

position

0.17

Activations Density 0.049%

technical terms and functions related to programming or software development

No Comments

No Known Activations