INDEX

Explanations

references to halfway houses

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

byt

-0.15

ussy

-0.15

qli

-0.14

ecom

-0.14

 Television

-0.14

 television

-0.14

mrt

-0.13

 breat

-0.13

ÑĮÐ¾Ð³Ð¾Ð´

-0.13

utm

-0.13

POSITIVE LOGITS

 teens

0.23

 teen

0.21

 wilderness

0.20

yrs

0.20

 Intl

0.19

 Teens

0.19

0.18

 Wilderness

0.18

gov

0.18

kid

0.18

Activations Density 0.000%

references to halfway houses

No Comments

No Known Activations