INDEX

Explanations

phrases related to dining experiences and unique restaurant settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

opher

-0.18

Ð³Ð»

-0.17

trand

-0.15

 Hilton

-0.15

 tract

-0.15

><?

-0.14

mer

-0.14

Zoom

-0.14

ooth

-0.14

POSITIVE LOGITS

0.17

 Funktion

0.17

ÃŃsto

0.16

odash

0.15

.social

0.15

 Urban

0.14

_MI

0.14

 transient

0.14

Activations Density 0.098%

phrases related to dining experiences and unique restaurant settings

No Comments

No Known Activations