INDEX

Explanations

phrases that indicate inspiration or influence from various sources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 Ø§ÙĦØ°

-0.16

TA

-0.15

ifar

-0.14

à¸«à¸§

-0.14

upa

-0.14

isku

-0.14

oglob

-0.14

anto

-0.14

yonel

-0.14

AppBundle

-0.14

POSITIVE LOGITS

pas

0.15

ìĩ

0.14

itura

0.14

iaux

0.13

 lessons

0.13

cap

0.13

cord

0.13

Band

0.13

cats

0.13

ëıĻ

0.13

Activations Density 0.024%

phrases that indicate inspiration or influence from various sources

No Comments

No Known Activations