INDEX

Explanations

terms related to food and dining experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 whose

-0.15

 Stern

-0.14

Ã§os

-0.14

quette

-0.14

Ã©rt

-0.14

 along

-0.14

ety

-0.13

 Stoke

-0.13

iffe

-0.13

 Generator

-0.13

POSITIVE LOGITS

oose

0.18

odied

0.17

Ã¼h

0.16

.ib

0.15

à¹ĥ

0.15

achuset

0.14

inent

0.13

OOK

0.13

kok

0.13

 kino

0.13

Activations Density 0.093%

terms related to food and dining experiences

No Comments

No Known Activations