INDEX

Explanations

instances of the word "dialogue" as well as related discussions around the concept of dialogue

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

lili

-0.20

¥Ĳ

-0.16

aso

-0.15

alli

-0.15

aging

-0.15

ãĥ¼ãĥ«ãĥī

-0.14

Ø§ÙĤÙĦ

-0.14

iever

-0.14

coc

-0.14

elerik

-0.14

POSITIVE LOGITS

proof

0.15

.apiUrl

0.15

ative

0.14

.LA

0.14

elves

0.13

engo

0.13

 extents

0.13

GenericType

0.13

evice

0.13

Activations Density 0.004%

instances of the word "dialogue" as well as related discussions around the concept of dialogue

No Comments

No Known Activations