INDEX

Explanations

the term "each" indicating quantity or distribution

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 doGet

-0.15

 Invent

-0.15

.hex

-0.14

 stro

-0.14

inge

-0.14

 ëĴ

-0.14

Maz

-0.13

uib

-0.13

ichen

-0.13

POSITIVE LOGITS

usch

0.17

Ð²Ð°Ð¹

0.15

okie

0.15

Ð»Ð°Ð²

0.15

ghan

0.15

ittings

0.15

ichtig

0.14

éı¡

0.14

polator

0.14

ecret

0.14

Activations Density 0.033%

the term "each" indicating quantity or distribution

No Comments

No Known Activations