INDEX

Explanations

instances of significant change or turning points in a narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

lbrace

-0.14

raÄį

-0.14

urs

-0.14

izr

-0.13

isk

-0.13

ÑĨÐµÐ¼

-0.13

µ¬

-0.13

ëħĦìĹĲëĬĶ

-0.13

inness

-0.13

POSITIVE LOGITS

 things

0.36

things

0.31

 Things

0.28

Things

0.27

 disaster

0.24

 something

0.23

 fate

0.23

 circumstances

0.23

 circumstance

0.23

 Something

0.21

Activations Density 0.234%

instances of significant change or turning points in a narrative

No Comments

No Known Activations