INDEX

Explanations

terms related to licensing and attribution for creative works

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

gross

-0.17

 Rowe

-0.16

anders

-0.16

ÐµÑģÑĤÑĮ

-0.15

imm

-0.14

shan

-0.14

 gross

-0.14

Imm

-0.14

imm

-0.14

 gelmiÅŁ

-0.14

POSITIVE LOGITS

azio

0.16

antium

0.15

Î¹Ïİ

0.14

áº¥n

0.14

unal

0.14

ÎµÎ¹Î¿

0.14

umbn

0.14

.ob

0.14

aland

0.14

TextInput

0.14

Activations Density 0.004%

terms related to licensing and attribution for creative works

No Comments

No Known Activations