INDEX

Explanations

references to planned activities or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

aat

-0.16

ic

-0.16

oÅ¾

-0.14

iker

-0.14

attles

-0.14

 Graves

-0.13

æį®

-0.13

Rum

-0.13

arrant

-0.13

POSITIVE LOGITS

erus

0.16

erin

0.15

irt

0.15

Touches

0.15

ings

0.14

vig

0.14

ulen

0.14

zipcode

0.14

mtx

0.14

isters

0.14

Activations Density 0.006%

references to planned activities or events

No Comments

No Known Activations