INDEX

Explanations

references to historical events and specific locations

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

OnInit

-0.16

.scalablytyped

-0.14

lue

-0.14

emmel

-0.14

strup

-0.14

 EntityState

-0.14

ublish

-0.14

reesome

-0.13

ypy

-0.13

uster

-0.13

POSITIVE LOGITS

rel

0.16

Rel

0.15

ABSPATH

0.15

qu

0.14

rel

0.14

_blocking

0.14

inant

0.14

Le

0.14

 trades

0.14

ahlen

0.13

Activations Density 0.121%

references to historical events and specific locations

No Comments

No Known Activations