INDEX

Explanations

references to mathematical equations or scientific notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

byn

-0.14

æĲ¬

-0.14

egot

-0.14

uada

-0.14

lass

-0.14

Injector

-0.14

Fet

-0.14

PFN

-0.14

 Charging

-0.13

ovsky

-0.13

POSITIVE LOGITS

ught

0.15

iday

0.15

.oracle

0.15

cheid

0.14

ais

0.14

itty

0.14

aign

0.14

 wheel

0.13

ICY

0.13

Activations Density 0.000%

references to mathematical equations or scientific notation

No Comments

No Known Activations