INDEX

Explanations

references to time and occurrences of events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ish

-0.18

uma

-0.15

 latter

-0.15

ing

-0.14

uala

-0.14

ump

-0.14

otal

-0.14

bjerg

-0.13

ened

-0.13

ublic

-0.13

POSITIVE LOGITS

 round

0.28

 around

0.26

Around

0.26

round

0.26

-round

0.23

 Around

0.23

-ci

0.22

around

0.22

-around

0.21

Round

0.21

Activations Density 0.030%

references to time and occurrences of events

No Comments

No Known Activations