INDEX

Explanations

references related to location and personal experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

jezd

-0.16

etroit

-0.15

imson

-0.15

enville

-0.15

LER

-0.14

>[]

-0.14

Detach

-0.14

braska

-0.13

(/^\

-0.13

cxx

-0.13

POSITIVE LOGITS

so

0.96

æīĢä»¥

0.68

ï¼ĮæīĢä»¥

0.63

So

0.58

so

0.57

So

0.55

 sÃ¥

0.48

 nÃªn

0.47

 therefore

0.47

ãģ®ãģ§

0.46

Activations Density 0.896%

references related to location and personal experiences

No Comments

No Known Activations