INDEX

Explanations

formal definitions and structured legal or technical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

-0.17

 Downs

-0.15

 Accord

-0.15

 Jian

-0.15

 PÃ©

-0.15

ãģıãģł

-0.14

 unders

-0.14

rab

-0.14

POSITIVE LOGITS

èĺ

0.16

ungs

0.15

/stretch

0.15

uber

0.15

éĢ¸

0.15

&E

0.15

ptom

0.14

yor

0.14

OptionsMenu

0.14

.MixedReality

0.14

Activations Density 0.015%

formal definitions and structured legal or technical terms

No Comments

No Known Activations