INDEX

Explanations

commands or suggestions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

sx

-0.17

olland

-0.16

armac

-0.15

iv

-0.15

pat

-0.14

oin

-0.14

yla

-0.14

utherland

-0.14

arrison

-0.14

ogle

-0.14

POSITIVE LOGITS

ting

0.25

tings

0.20

ÃŃcia

0.20

us

0.20

zte

0.17

itia

0.17

nici

0.17

 Glob

0.16

achable

0.16

ts

0.15

Activations Density 0.024%

commands or suggestions

No Comments

No Known Activations