INDEX

Explanations

instances of actions and their consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

enheim

-0.18

enties

-0.17

Ã¤nn

-0.16

ĨĴ

-0.15

baugh

-0.15

idel

-0.15

entin

-0.14

ä»Ĭ

-0.14

unless

-0.14

prises

-0.14

POSITIVE LOGITS

 upon

0.25

 rather

0.24

 instead

0.22

Upon

0.21

 Upon

0.21

 Rather

0.21

 feeling

0.21

 after

0.21

Rather

0.20

 Unable

0.20

Activations Density 0.259%

instances of actions and their consequences

No Comments

No Known Activations