INDEX

Explanations

instances of cultural references and notable names in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ajor

-0.14

wow

-0.14

Ð¹

-0.14

 Aires

-0.14

Disposed

-0.14

ameleon

-0.14

Yep

-0.13

anik

-0.13

 Calder

-0.13

âĢį

-0.13

POSITIVE LOGITS

(TM

0.19

Teh

0.18

plode

0.17

 DERP

0.17

 proletariat

0.16

ÎŃÎ»

0.15

teh

0.15

 smrt

0.15

pw

0.14

Activations Density 1.746%

instances of cultural references and notable names in the text

No Comments

No Known Activations