INDEX

Explanations

qualities and characteristics related to product performance and usability

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

iant

-0.16

ustos

-0.15

rowse

-0.15

CDATA

-0.15

_alignment

-0.14

lfw

-0.14

TexImage

-0.14

vyk

-0.13

erde

-0.13

POSITIVE LOGITS

hek

0.17

Ka

0.15

olid

0.14

ivi

0.14

 factor

0.14

amba

0.14

ilst

0.14

eka

0.14

 should

0.13

inator

0.13

Activations Density 0.558%

qualities and characteristics related to product performance and usability

No Comments

No Known Activations