INDEX

Explanations

references to diplomats or diplomatic titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

CLU

-0.15

ìĬµ

-0.15

ylvania

-0.14

Ð¾Ð¿Ð¾Ð»

-0.14

 ucwords

-0.14

lore

-0.14

erged

-0.14

_MATH

-0.14

 Toll

-0.13

ulla

-0.13

POSITIVE LOGITS

 embassy

0.37

 Embassy

0.35

 diplomatic

0.30

 ambassador

0.29

 diplomat

0.29

Emb

0.29

emb

0.29

 diplomats

0.28

 Ambassador

0.27

 Dipl

0.26

Activations Density 0.208%

references to diplomats or diplomatic titles

No Comments

No Known Activations