INDEX

Explanations

measurements related to size or dimensions

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

ess

-0.18

DOI

-0.15

ÏħÎ³

-0.15

ult

-0.15

pants

-0.14

uby

-0.14

 Ø±ÙħØ²

-0.14

 conventional

-0.14

omite

-0.14

ernal

-0.13

POSITIVE LOGITS

@js

0.16

strand

0.16

bers

0.16

èĥ¶

0.15

eters

0.15

jab

0.15

endoza

0.15

kuk

0.14

jejer

0.14

aturity

0.13

Activations Density 0.007%

measurements related to size or dimensions

No Comments

No Known Activations