INDEX

Explanations

phrases that indicate expectations or comparisons to typical experiences

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

ellig

-0.16

ÙĪÙĬØª

-0.14

oksen

-0.14

 sleeper

-0.14

auce

-0.14

oya

-0.14

ikki

-0.14

antom

-0.14

.TryParse

-0.14

stÃ¥

-0.14

POSITIVE LOGITS

 typical

0.35

typ

0.29

 typically

0.26

 Typical

0.24

Typ

0.23

typically

0.22

 Typically

0.21

 commonly

0.21

 would

0.20

 common

0.18

Activations Density 0.175%

phrases that indicate expectations or comparisons to typical experiences

No Comments

No Known Activations