INDEX

Explanations

mentions of books or literary works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

zim

-0.16

uft

-0.16

Å¾i

-0.15

eydi

-0.15

asca

-0.15

ellido

-0.15

Å¾

-0.15

amedi

-0.15

alloca

-0.15

oggler

-0.15

POSITIVE LOGITS

æħİ

0.15

sa

0.14

athon

0.14

 Craig

0.14

/effects

0.14

.opens

0.14

 Brewing

0.14

 gangbang

0.13

ney

0.13

Craig

0.13

Activations Density 0.001%

mentions of books or literary works

No Comments

No Known Activations