INDEX

Explanations

references to the word "sonic"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

jong

-0.17

 Chapel

-0.15

 late

-0.15

hap

-0.14

own

-0.14

udes

-0.14

 llama

-0.14

-0.13

eus

-0.13

POSITIVE LOGITS

 ãĤ¢ãĤ¤

0.15

/gpl

0.15

tat

0.15

cran

0.14

_PROGRAM

0.14

adar

0.14

-Javadoc

0.14

enton

0.14

pollo

0.14

webdriver

0.14

Activations Density 0.006%

references to the word "sonic"

No Comments

No Known Activations