INDEX

Explanations

references to U.S. states and their characteristics

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

agit

-0.16

berger

-0.15

obl

-0.15

 pros

-0.15

mod

-0.15

Hed

-0.15

 pron

-0.14

hem

-0.14

pul

-0.14

iu

-0.14

POSITIVE LOGITS

ereal

0.16

 Ø§ÙĦØ§ØŃ

0.16

osate

0.15

 ê°ĲìĤ¬

0.15

verity

0.15

hos

0.14

ansas

0.14

forma

0.14

MMI

0.14

Ø±ÙĤ

0.14

Activations Density 0.143%

references to U.S. states and their characteristics

No Comments

No Known Activations