INDEX

Explanations

file paths and import statements in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 Albums

-0.17

asio

-0.16

itou

-0.15

geh

-0.15

agar

-0.15

rane

-0.14

arme

-0.14

eced

-0.14

âĢķâĢķâĢķâĢķ

-0.14

loub

-0.14

POSITIVE LOGITS

 Hund

0.15

 Harr

0.14

 thick

0.14

 Stewart

0.14

sim

0.13

acco

0.13

amoto

0.13

DO

0.13

antic

0.13

Gad

0.13

Activations Density 0.002%

file paths and import statements in code

No Comments

No Known Activations