INDEX

Explanations

references to specific topics or items being discussed

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

mons

-0.15

rz

-0.15

 Crane

-0.14

pl

-0.14

.pm

-0.14

MON

-0.14

 khung

-0.14

-0.13

 activity

-0.13

POSITIVE LOGITS

pective

0.16

ovsky

0.16

PropertyValue

0.15

lander

0.15

quent

0.15

aju

0.15

ovacÃŃ

0.15

ylko

0.14

Ã©lÃ©

0.14

LocalizedString

0.14

Activations Density 0.082%

references to specific topics or items being discussed

No Comments

No Known Activations