INDEX

Explanations

elements related to confidentiality and usage restrictions of information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

dera

-0.18

io

-0.15

pil

-0.15

acre

-0.15

SOR

-0.15

Enumerable

-0.14

ote

-0.14

 vests

-0.14

 Advisory

-0.14

ior

-0.14

POSITIVE LOGITS

 nÃło

0.16

 unless

0.16

htable

0.15

Ã¤t

0.14

.createClass

0.14

ieten

0.14

nÃ¡

0.14

aidu

0.14

obao

0.14

hz

0.14

Activations Density 0.155%

elements related to confidentiality and usage restrictions of information

No Comments

No Known Activations