INDEX

Explanations

technical code-related terms and programming concepts

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

EB

-0.16

omor

-0.15

IB

-0.15

rays

-0.15

 factors

-0.14

 nursing

-0.14

ray

-0.14

 Nursing

-0.14

 factor

-0.14

adm

-0.14

POSITIVE LOGITS

Ni

0.31

Ni

0.28

 Flow

0.25

(flow

0.24

 flow

0.23

flow

0.22

.Flow

0.22

-flow

0.22

Flow

0.22

.flow

0.22

Activations Density 0.001%

technical code-related terms and programming concepts

No Comments

No Known Activations

technical code-related terms and programming concepts

No Comments

No Known Activations