INDEX

Explanations

references to programming or technical elements related to computer science

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

uke

-0.16

 Grass

-0.15

Nah

-0.15

lia

-0.14

trand

-0.14

diag

-0.14

oha

-0.14

oucher

-0.14

tractive

-0.13

POSITIVE LOGITS

å¯

0.16

kin

0.16

 dziew

0.15

egie

0.15

<?>

0.15

ccione

0.14

-NLS

0.14

ãģķãģĦ

0.14

okable

0.14

 barr

0.14

Activations Density 0.123%

references to programming or technical elements related to computer science

No Comments

No Known Activations