INDEX

Explanations

numerical identifiers or codes related to publications and research articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

uther

-0.17

um

-0.17

hol

-0.16

ummy

-0.16

ault

-0.15

Sink

-0.15

ÏĢÎ¿ÏĦÎµ

-0.15

ths

-0.15

pedia

-0.15

 Sink

-0.14

POSITIVE LOGITS

st

0.29

uhl

0.18

ì§ľ

0.17

sou

0.16

oland

0.16

rst

0.15

DirectoryName

0.15

 ÑĥÐ¶

0.15

/XMLSchema

0.14

Activations Density 0.118%

numerical identifiers or codes related to publications and research articles

No Comments

No Known Activations