INDEX

Explanations

phrases relating to documentation and support processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

æĬĬ

-0.21

abb

-0.16

-touch

-0.15

 blew

-0.15

JsonValue

-0.15

turn

-0.15

 threw

-0.14

kenin

-0.14

dee

-0.14

 tore

-0.14

POSITIVE LOGITS

 given

0.21

 taken

0.20

 shown

0.20

 thrown

0.18

 kept

0.17

 seen

0.16

ugas

0.16

given

0.16

 inventor

0.15

Lup

0.15

Activations Density 0.273%

phrases relating to documentation and support processes

No Comments

No Known Activations