INDEX

Explanations

references to data collection and privacy practices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

elage

-0.18

lee

-0.18

cko

-0.15

czy

-0.15

iedad

-0.14

 takson

-0.14

Ø¬ÙĬ

-0.14

.fail

-0.13

ierz

-0.13

iedades

-0.13

POSITIVE LOGITS

tron

0.18

IPH

0.18

åĮ

0.17

raw

0.17

ga

0.16

oria

0.16

 anonym

0.16

ga

0.15

Activations Density 0.012%

references to data collection and privacy practices

No Comments

No Known Activations