INDEX

Explanations

phrases indicating technical or legal criteria

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

Ø¯Ø¯

-0.15

 Ridley

-0.15

arde

-0.15

PropTypes

-0.14

Eg

-0.14

 lÃ²ng

-0.14

iren

-0.13

avier

-0.13

 pylint

-0.13

 jadx

-0.13

POSITIVE LOGITS

overn

0.17

 Cunningham

0.15

/edit

0.15

unga

0.15

HEMA

0.14

 anlamda

0.14

.EntityFramework

0.14

ãĥ³ãĥī

0.14

yte

0.14

avicon

0.14

Activations Density 0.079%

phrases indicating technical or legal criteria

No Comments

No Known Activations