INDEX

Explanations

references to credit and attribution in texts

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

awe

-0.17

Filed

-0.17

sam

-0.14

Î¸Î·

-0.14

Cancelable

-0.14

af

-0.13

 equation

-0.13

Egg

-0.13

ToPoint

-0.13

 foreign

-0.13

POSITIVE LOGITS

enek

0.16

exels

0.16

elow

0.15

å½¼

0.15

iler

0.15

è¢

0.14

ODO

0.14

Rug

0.14

eria

0.14

Activations Density 0.001%

references to credit and attribution in texts

No Comments

No Known Activations