INDEX

Explanations

mathematical symbols and notation used in equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

bens

-0.15

 Intervention

-0.15

deo

-0.14

lice

-0.14

Ð±ÑĢÐ°

-0.14

 Trev

-0.14

positor

-0.13

æŃ

-0.13

boom

-0.13

Ide

-0.13

POSITIVE LOGITS

psc

0.18

Wunused

0.15

 Hancock

0.15

 incom

0.14

rador

0.14

©

0.14

 Nicar

0.14

 fossil

0.13

Activations Density 0.051%

mathematical symbols and notation used in equations

No Comments

No Known Activations