INDEX

Explanations

references to content and information delivery

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

aber

-0.16

olis

-0.15

 Garrison

-0.14

 hence

-0.14

/browser

-0.14

anou

-0.14

ths

-0.14

odzi

-0.14

acji

-0.14

POSITIVE LOGITS

oday

0.17

Hod

0.15

_RT

0.14

pend

0.14

.FLAG

0.14

Äįer

0.14

iz

0.13

ãģ¦ãĤĤ

0.13

gra

0.13

 Malk

0.13

Activations Density 0.035%

references to content and information delivery

No Comments

No Known Activations