INDEX

Explanations

sequences of actions and interactions among characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ullet

-0.17

erner

-0.16

 Traverse

-0.15

urf

-0.15

loh

-0.15

alan

-0.14

Ø§Ø¨Ø±

-0.14

 Bret

-0.14

Concurrency

-0.14

yon

-0.14

POSITIVE LOGITS

then

0.23

 then

0.23

 Then

0.21

 THEN

0.20

Then

0.20

.then

0.19

THEN

0.17

_then

0.16

 began

0.16

 proced

0.16

Activations Density 0.296%

sequences of actions and interactions among characters

No Comments

No Known Activations