INDEX

Explanations

technical terms related to programming and data 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

ince

-0.13

ocument

-0.13

iaux

-0.13

/gpl

-0.13

ependency

-0.12

Inspectable

-0.12

èĮ

-0.12

ijkstra

-0.11

itals

-0.11

ê²¬

-0.11

POSITIVE LOGITS

Im

1.28

im

1.27

Im

1.20

im

1.13

-im

1.10

_im

1.06

.im

1.03

(im

0.98

IM

0.96

IM

0.96

Activations Density 0.755%

technical terms related to programming and data structures

No Comments

No Known Activations