INDEX

Explanations

terms related to community oversight, preservation, and various fields of academic and professional studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ãĥ¬ãĥ¼

-0.13

Ð¾Ð»ÑĮ

-0.13

 contrad

-0.13

quit

-0.13

æĭĴ

-0.13

ÑĥÐ·Ñĭ

-0.13

Ð½Ð°Ðº

-0.13

ibbon

-0.13

 Slee

-0.13

iyat

-0.12

POSITIVE LOGITS

iddi

0.15

redients

0.15

ãĥ¡ãĥ©

0.14

TI

0.14

 Briggs

0.14

mos

0.13

CodeAt

0.13

.UIManager

0.13

_AXIS

0.13

arters

0.13

Activations Density 0.069%

terms related to community oversight, preservation, and various fields of academic and professional studies

No Comments

No Known Activations