INDEX

Explanations

words related to entertainment or content classification

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

plorer

-0.16

rav

-0.16

ÑĤÐ¸Ðº

-0.15

atism

-0.15

imbus

-0.15

ãĥ¼ãĥ³

-0.14

/workspace

-0.14

TestFixture

-0.14

abay

-0.14

paces

-0.14

POSITIVE LOGITS

0.19

ergus

0.18

0.15

zw

0.15

.training

0.15

Ð¾ÐºÐ¾Ð½

0.14

 Curtain

0.14

ura

0.14

Tw

0.14

 Prest

0.14

Activations Density 0.000%

words related to entertainment or content classification

No Comments

No Known Activations