INDEX

Explanations

words related to quantifiable measurements or specifications

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

bat

-0.19

 Spicer

-0.17

assi

-0.17

Rug

-0.16

asil

-0.15

rug

-0.15

azzi

-0.15

znÃ¡m

-0.15

Ø±Ø¨

-0.15

Ã©c

-0.14

POSITIVE LOGITS

esser

0.20

 respectively

0.19

 respective

0.18

arella

0.15

enstein

0.15

WithContext

0.15

ÐķÐ¡

0.15

 ÑģÐ¾Ð¾ÑĤÐ²ÐµÑĤ

0.14

itted

0.14

áº½

0.14

Activations Density 0.055%

words related to quantifiable measurements or specifications

No Comments

No Known Activations