INDEX

Explanations

references to "load" in various contexts

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

assen

-0.17

ophon

-0.15

zo

-0.15

Ú¯Ø±

-0.15

ake

-0.14

Ð½Ð¸Ð¼Ð°

-0.14

 Äĥn

-0.14

ode

-0.14

akes

-0.14

 Booth

-0.14

POSITIVE LOGITS

Unload

0.29

ings

0.25

-bearing

0.25

shed

0.23

rant

0.20

Balancer

0.19

edException

0.18

bearing

0.18

 shedding

0.18

unload

0.17

Activations Density 0.024%

references to "load" in various contexts

No Comments

No Known Activations