INDEX

Explanations

phrases emphasizing exclusivity or limitation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

anguage

-0.18

olley

-0.17

ju

-0.16

idden

-0.14

oka

-0.14

.Invariant

-0.14

juan

-0.14

ju

-0.14

Ð·Ñĥ

-0.14

oshi

-0.14

POSITIVE LOGITS

 handful

0.21

few

0.20

one

0.19

 mÃ¡lo

0.17

ONE

0.16

few

0.16

kus

0.16

Few

0.16

Few

0.15

Canonical

0.14

Activations Density 0.092%

phrases emphasizing exclusivity or limitation

No Comments

No Known Activations