INDEX

Explanations

references to storytelling and narratives, particularly involving legends and fairy tales

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ossier

-0.20

ollapse

-0.16

ategories

-0.14

ç·

-0.14

ween

-0.14

utomation

-0.14

ovna

-0.13

åľ°ä¸ĭ

-0.13

uppy

-0.13

rob

-0.13

POSITIVE LOGITS

 tales

0.15

ices

0.15

OTES

0.15

adia

0.15

ARIO

0.14

bÄĽh

0.14

 stories

0.14

ola

0.14

utan

0.14

Activations Density 0.150%

references to storytelling and narratives, particularly involving legends and fairy tales

No Comments

No Known Activations