INDEX

Explanations

references to cooking and food experiences

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

vice

-0.17

unan

-0.15

kick

-0.14

 Starter

-0.14

alance

-0.14

anden

-0.14

reur

-0.14

erdale

-0.14

raf

-0.14

 Void

-0.14

POSITIVE LOGITS

lili

0.15

ITTE

0.14

[_

0.14

INED

0.14

ãĥ¼ãĥĳ

0.14

ê¹¨

0.14

.mods

0.13

 ling

0.13

uce

0.13

rig

0.13

Activations Density 0.076%

references to cooking and food experiences

No Comments

No Known Activations