INDEX

Explanations

geographic locations and states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

 Patt

-0.17

laz

-0.15

oes

-0.15

 Giov

-0.15

aths

-0.15

-0.14

athon

-0.14

POSITIVE LOGITS

Ð½Ð°ÑĤ

0.17

 tÃ´

0.15

 Ø§ÙĦØ±Ùħ

0.14

ptune

0.14

achten

0.14

.onView

0.14

addock

0.14

ç±į

0.14

amo

0.14

 Crew

0.14

Activations Density 0.074%

geographic locations and states

No Comments

No Known Activations