INDEX

Explanations

references to scientific or technical terminology related to research

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

 Hamm

-0.13

ÃĹ↵↵

-0.13

ÑĥÑĩÐ°

-0.13

etadata

-0.13

 Kahn

-0.13

ichert

-0.12

 Fortune

-0.12

 Ð¨ÐµÐ²

-0.12

isto

-0.12

POSITIVE LOGITS

0.30

$L

0.29

 à¤²

0.28

ÂłL

0.26

 ÐĽ

0.26

 ÙĦ

0.26

_l

0.25

.L

0.24

 Ð»

0.24

Activations Density 1.114%

references to scientific or technical terminology related to research

No Comments

No Known Activations