INDEX

Explanations

words 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

halt

-0.16

Numbers

-0.15

ingo

-0.14

 Wich

-0.13

 Gore

-0.13

erp

-0.13

floor

-0.13

Systems

-0.13

amburger

-0.13

POSITIVE LOGITS

zano

0.15

enses

0.15

 Ravens

0.14

osas

0.14

atto

0.14

attery

0.14

adÄ±k

0.14

Ä±ÅŁÄ±

0.13

.typ

0.13

itched

0.13

Activations Density 0.000%

words related to entertainment

No Comments

No Known Activations