INDEX

Explanations

references to discussions or statements made by individuals in a given context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

lacak

-0.15

lix

-0.15

akh

-0.15

Ãłi

-0.14

ful

-0.14

Asked

-0.14

èªī

-0.14

 tens

-0.14

isu

-0.13

Narrated

-0.13

POSITIVE LOGITS

 shared

0.29

 states

0.27

 state

0.25

 shares

0.24

shared

0.23

 sharing

0.22

_shared

0.22

 claims

0.21

states

0.20

 share

0.20

Activations Density 0.158%

references to discussions or statements made by individuals in a given context

No Comments

No Known Activations