INDEX

Explanations

references to teachings or instructions about behaviors and societal issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

atar

-0.17

 Destructor

-0.15

wm

-0.14

 Mister

-0.14

 swept

-0.14

ÑıÐ¶

-0.13

 turkey

-0.13

assoc

-0.13

ander

-0.13

verty

-0.13

POSITIVE LOGITS

 itself

0.16

IDD

0.16

ISCO

0.15

zik

0.14

pper

0.14

TTY

0.14

Mig

0.14

mobx

0.14

IOD

0.13

DataContract

0.13

Activations Density 1.177%

references to teachings or instructions about behaviors and societal issues

No Comments

No Known Activations