INDEX

Explanations

references to Pokémon and their related characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

reur

-0.15

.bin

-0.15

ipel

-0.14

roc

-0.14

ifen

-0.14

ILON

-0.14

 Burl

-0.14

omite

-0.14

 tort

-0.14

.AutoComplete

-0.14

POSITIVE LOGITS

yan

0.16

oad

0.16

emain

0.15

 Rear

0.14

ç¬ĳ

0.14

 Rarity

0.14

atal

0.14

elib

0.14

VertexArray

0.13

paging

0.13

Activations Density 0.006%

references to Pokémon and their related characteristics

No Comments

No Known Activations