INDEX

Explanations

references to programming and software development concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 immortal

-0.17

 Rubin

-0.16

aire

-0.15

auf

-0.15

ãĥģãĥ¥

-0.15

ennon

-0.14

ael

-0.14

opes

-0.14

aus

-0.14

ecess

-0.14

POSITIVE LOGITS

 build

0.25

build

0.24

 Build

0.24

 BUILD

0.22

BUILD

0.21

.build

0.20

 targets

0.20

 Builds

0.19

 builds

0.19

BuildContext

0.19

Activations Density 0.197%

references to programming and software development concepts

No Comments

No Known Activations