INDEX

Explanations

proper nouns and names associated with legal or historical contexts

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

heits

-0.15

anium

-0.15

ioned

-0.15

APE

-0.14

Parcel

-0.14

ILA

-0.14

 Giants

-0.14

 Giant

-0.14

abilit

-0.14

ppo

-0.14

POSITIVE LOGITS

 Lord

0.24

 Lords

0.24

 lord

0.24

Lord

0.23

çĪµ

0.22

 Baron

0.21

 count

0.21

 LORD

0.20

 lords

0.19

 Count

0.19

Activations Density 0.092%

proper nouns and names associated with legal or historical contexts

No Comments

No Known Activations