INDEX

Explanations

references to CNN and its programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

EFA

-0.16

-Semit

-0.16

oli

-0.15

amba

-0.14

ori

-0.14

.TestCase

-0.14

ìĺ¥

-0.14

anut

-0.14

ÏĦÎ±ÏĤ

-0.14

ëĭĪìķĦ

-0.14

POSITIVE LOGITS

CNN

0.33

CNN

0.30

cnn

0.23

NN

0.20

 Anderson

0.20

 anchor

0.19

anchor

0.18

anchors

0.18

Money

0.17

edition

0.17

Activations Density 0.017%

references to CNN and its programming

No Comments

No Known Activations