INDEX

Explanations

phrases or concepts related to "entertainment."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

kili

-0.18

akan

-0.16

amac

-0.16

RuntimeObject

-0.15

Ø±Ø¯Ùĩ

-0.15

agal

-0.15

istique

-0.15

rak

-0.15

ãĥ§

-0.15

agate

-0.15

POSITIVE LOGITS

outh

0.17

 universal

0.16

iversal

0.15

cid

0.14

altern

0.14

se

0.14

Activations Density 0.024%

phrases or concepts related to "entertainment."

No Comments

No Known Activations