INDEX

Explanations

terms related to transportation and logistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

intosh

-0.16

gers

-0.14

 Gravity

-0.14

ÑĢÐ¸Ð²

-0.14

red

-0.14

umber

-0.14

NECT

-0.13

berger

-0.13

rooms

-0.13

Vit

-0.13

POSITIVE LOGITS

ational

0.33

ations

0.31

ive

0.24

ATION

0.22

ers

0.21

ainment

0.21

atio

0.20

ATIONAL

0.20

.googleapis

0.20

ation

0.19

Activations Density 0.020%

terms related to transportation and logistics

No Comments

No Known Activations