INDEX

Explanations

numerical values or dates

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

ire

-0.17

undle

-0.15

iri

-0.15

andle

-0.15

zin

-0.14

uzzer

-0.14

uzu

-0.14

och

-0.13

umer

-0.13

grant

-0.13

POSITIVE LOGITS

leon

0.15

rops

0.15

Eb

0.14

endforeach

0.13

hoe

0.13

amoto

0.13

erais

0.13

ieÅ¼

0.13

{*

0.13

owns

0.13

Activations Density 0.026%

numerical values or dates

No Comments

No Known Activations