INDEX

Explanations

references to personal experiences and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

rowsable

-0.15

.scalajs

-0.14

ocs

-0.14

gne

-0.14

OUN

-0.13

 Overse

-0.13

 IonicModule

-0.13

makt

-0.13

 Rosenstein

-0.13

uctions

-0.13

POSITIVE LOGITS

duk

0.17

lint

0.17

ASA

0.15

Pep

0.14

CU

0.14

resses

0.14

 profiling

0.13

Heb

0.13

vvm

0.13

agi

0.13

Activations Density 0.215%

references to personal experiences and actions

No Comments

No Known Activations