INDEX

Explanations

years, particularly recent ones that define specific events or trends

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ild

-0.16

 åħŃ

-0.16

ocode

-0.16

arda

-0.15

à¸©

-0.15

 Majority

-0.15

eling

-0.15

.qq

-0.15

six

-0.14

LayoutConstraint

-0.14

POSITIVE LOGITS

0.24

0.22

0.21

0.19

0.18

0.17

0.16

zwe

0.16

BD

0.15

Activations Density 0.037%

years, particularly recent ones that define specific events or trends

No Comments

No Known Activations