INDEX

Explanations

references to significant events or changes related to "groundbreaking" projects or concepts

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

æľĭ

-0.18

ÌĨ

-0.18

ett

-0.15

akes

-0.15

ipi

-0.14

cks

-0.14

ayo

-0.14

lite

-0.14

Kob

-0.14

mono

-0.14

POSITIVE LOGITS

hog

0.31

truth

0.25

-breaking

0.25

_truth

0.23

breaking

0.23

 truth

0.23

 ground

0.23

 breaking

0.23

Truth

0.22

-floor

0.21

Activations Density 0.009%

references to significant events or changes related to "groundbreaking" projects or concepts

No Comments

No Known Activations