INDEX

Explanations

references to educational institutions and levels

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

sm

-0.16

edm

-0.15

ystems

-0.14

emez

-0.14

abyrinth

-0.14

ady

-0.14

 Cumhur

-0.14

stime

-0.14

bane

-0.13

POSITIVE LOGITS

 Ricky

0.15

Ð¡Ðŀ

0.15

testdata

0.14

Paste

0.14

OLON

0.14

 Paste

0.14

ksam

0.14

á»ĩ

0.14

ãĥĨãĤ£

0.14

Zwe

0.13

Activations Density 0.006%

references to educational institutions and levels

No Comments

No Known Activations