INDEX

Explanations

dates and locations associated with events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

asm

-0.15

ener

-0.15

ippers

-0.14

ials

-0.14

é¨

-0.14

itate

-0.14

iton

-0.13

ileen

-0.13

stead

-0.13

itia

-0.13

POSITIVE LOGITS

anja

0.18

 Voll

0.15

 Snowden

0.15

erli

0.15

noticed

0.15

0.14

interop

0.14

compan

0.14

"group

0.14

Activations Density 0.002%

dates and locations associated with events

No Comments

No Known Activations