INDEX

Explanations

references to privacy and information security practices

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

adora

-0.14

.argmax

-0.14

metic

-0.14

lices

-0.13

YE

-0.13

rypto

-0.13

jedn

-0.13

utenberg

-0.13

reator

-0.13

POSITIVE LOGITS

TPL

0.16

eyin

0.15

AppName

0.15

tas

0.15

ANTE

0.15

antha

0.15

Geg

0.15

TRS

0.14

Perm

0.14

 ancest

0.14

Activations Density 0.255%

references to privacy and information security practices

No Comments

No Known Activations