INDEX

Explanations

locations and settings for events or activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

jos

-0.15

ahu

-0.14

usz

-0.14

 ÙĪØºÙĬØ±

-0.14

isle

-0.14

aliz

-0.13

estic

-0.13

 åĤ

-0.13

 Ð·Ð°ÑģÑĤ

-0.13

odel

-0.13

POSITIVE LOGITS

legates

0.15

iges

0.14

#=

0.14

ÙĪØ§ÙĦ

0.14

ÎºÏĮ

0.14

unya

0.14

legg

0.13

 McCl

0.13

cup

0.13

urnal

0.13

Activations Density 0.043%

locations and settings for events or activities

No Comments

No Known Activations