INDEX

Explanations

technical terms and references related to coding or programming structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Suppress

-0.16

agh

-0.15

.shapes

-0.15

apes

-0.14

ek

-0.14

VisualStyle

-0.14

allah

-0.13

ekk

-0.13

 Suppress

-0.13

LocalizedMessage

-0.13

POSITIVE LOGITS

 texture

0.28

tex

0.28

Tex

0.26

mip

0.26

 depth

0.25

Tex

0.24

 Texture

0.24

 Depth

0.24

tex

0.23

.tex

0.22

Activations Density 0.011%

technical terms and references related to coding or programming structures

No Comments

No Known Activations