INDEX

Explanations

instances of suggesting or proposing ideas or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ucha

-0.18

ackers

-0.17

von

-0.17

ulings

-0.15

ichael

-0.15

.synthetic

-0.15

isas

-0.14

ãģ¹ãģį

-0.14

Ø§ÙĨÙĩ

-0.14

Ð½Ð¸Ð¸

-0.14

POSITIVE LOGITS

ively

0.24

entially

0.18

ive

0.18

IVE

0.18

 ìĭ¶

0.17

ors

0.16

ons

0.15

 ìĤ¬íķŃ

0.15

iments

0.15

Activations Density 0.029%

instances of suggesting or proposing ideas or actions

No Comments

No Known Activations