INDEX

Explanations

references to measurements and configurations in scientific or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ome

-0.16

 kinds

-0.15

Readable

-0.15

exe

-0.14

baz

-0.14

urent

-0.14

rac

-0.14

imentos

-0.14

akens

-0.14

ral

-0.14

POSITIVE LOGITS

 enough

0.18

aghetti

0.16

/high

0.15

vr

0.14

 Enough

0.14

erc

0.14

Î¬Î²

0.14

 Kraj

0.14

gest

0.14

UIB

0.14

Activations Density 0.169%

references to measurements and configurations in scientific or technical contexts

No Comments

No Known Activations