INDEX

Explanations

references to specialized organizations or institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

-speaking

-0.17

ument

-0.17

ÑĮÐºÐ¾

-0.16

anz

-0.16

ernal

-0.15

suit

-0.15

adel

-0.15

\grid

-0.14

andle

-0.14

otton

-0.14

POSITIVE LOGITS

pieces

0.21

0.20

lify

0.19

most

0.18

ÑĦÐ¾ÑĢ

0.16

-left

0.16

Glyph

0.15

polate

0.15

ing

0.15

lain

0.15

Activations Density 0.059%

references to specialized organizations or institutions

No Comments

No Known Activations