INDEX

Explanations

quantities measured in tons

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ark

-0.16

assy

-0.16

em

-0.15

shr

-0.15

-0.14

ulg

-0.14

ec

-0.14

 final

-0.14

POSITIVE LOGITS

issen

0.17

ynchronously

0.16

hive

0.16

inox

0.14

 Øµ

0.14

ãģĽãģ¦

0.14

outine

0.14

meer

0.14

nam

0.14

ideos

0.14

Activations Density 0.002%

quantities measured in tons

No Comments

No Known Activations