INDEX

Explanations

programming concepts and operations related to data manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

eyen

-0.15

agle

-0.15

roj

-0.14

lf

-0.14

ingleton

-0.14

INGLE

-0.14

=default

-0.14

POSITIVE LOGITS

Ø·ÙĦ

0.16

gaard

0.15

/count

0.15

axter

0.14

/items

0.14

/item

0.14

rary

0.14

ìĥģìľĦ

0.13

inho

0.13

ItemAt

0.13

Activations Density 0.112%

programming concepts and operations related to data manipulation

No Comments

No Known Activations