INDEX

Explanations

relationships and dynamics between characters 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 @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

izon

-0.16

 EntityState

-0.15

itus

-0.15

 ==============================================================

-0.14

UDO

-0.14

ARP

-0.14

 ApplicationException

-0.14

ansa

-0.14

ynn

-0.14

eliac

-0.14

POSITIVE LOGITS

Wiki

0.15

wiki

0.15

 Bulk

0.14

combe

0.14

BOOST

0.14

 Floating

0.14

inema

0.13

strap

0.13

ColumnInfo

0.13

Activations Density 0.573%

relationships and dynamics between characters in a narrative

No Comments

No Known Activations