INDEX

Explanations

references to software components and their interactions

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

red

-0.18

ĨĴ

-0.15

RED

-0.15

Red

-0.15

onec

-0.15

RED

-0.15

 Bris

-0.15

ONEY

-0.15

-0.14

ardon

-0.14

POSITIVE LOGITS

 earlier

0.17

 ########.

0.16

 bait

0.15

ua

0.14

 Ð½ÐµÑĢ

0.14

æĽ´å¤ļ

0.14

mgr

0.14

_regularizer

0.14

_handles

0.13

ãĥ¼ãĥĲ

0.13

Activations Density 1.646%

references to software components and their interactions

No Comments

No Known Activations