INDEX

Explanations

introductory phrases that set up explanations or definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 Depths

-0.17

oldt

-0.16

readcr

-0.15

æµħ

-0.15

imb

-0.15

edin

-0.14

loh

-0.14

ÙĪØ§Ø±

-0.14

inder

-0.14

estroy

-0.14

POSITIVE LOGITS

anya

0.16

anton

0.15

luck

0.14

PointerType

0.14

ãĥĬãĥ¼

0.14

ny

0.14

BaseContext

0.14

 luck

0.13

Activations Density 0.088%

introductory phrases that set up explanations or definitions

No Comments

No Known Activations