INDEX

Explanations

phrases that emphasize long-term outcomes or considerations

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

Äįas

-0.16

loo

-0.16

arat

-0.16

 Romans

-0.15

 Chick

-0.15

elman

-0.15

ÏĥÎ¹

-0.15

hurst

-0.15

 Rockefeller

-0.15

popover

-0.14

POSITIVE LOGITS

 scheme

0.28

run

0.28

scheme

0.27

run

0.22

 schemes

0.21

 haul

0.21

 Scheme

0.21

Scheme

0.17

 game

0.17

Run

0.17

Activations Density 0.017%

phrases that emphasize long-term outcomes or considerations

No Comments

No Known Activations