INDEX

Explanations

terms associated with plot twists and surprises in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ierz

-0.16

ipple

-0.15

æ²¢

-0.15

ÑĢÐ¾Ð¿

-0.14

ethyst

-0.14

ÄĽÅ¾

-0.14

ieux

-0.14

Ø´ÙħØ§ÙĦÛĮ

-0.14

 Quadr

-0.13

lÄ±

-0.13

POSITIVE LOGITS

thal

0.17

ÑĢÐ°Ð±Ð°ÑĤ

0.16

ichen

0.16

inox

0.16

 twist

0.16

 Kraj

0.15

abyrinth

0.14

arily

0.14

Ã©d

0.13

 Sokol

0.13

Activations Density 0.029%

terms associated with plot twists and surprises in narratives

No Comments

No Known Activations