INDEX

Explanations

historical figures or entities associated with significant events or locations

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

ÐµÐ¼Ð°ÑĤÐ¸

-0.15

ensis

-0.15

occo

-0.15

$MESS

-0.15

aÅ¼

-0.15

ADVERTISEMENT

-0.14

kees

-0.14

mey

-0.13

tems

-0.13

EMENT

-0.13

POSITIVE LOGITS

oldt

0.14

un

0.14

ÐµÐ½ÐºÐ°

0.14

 Cele

0.13

or

0.13

Pom

0.13

inely

0.13

 Chand

0.13

 Roll

0.13

studio

0.13

Activations Density 0.140%

historical figures or entities associated with significant events or locations

No Comments

No Known Activations