INDEX

Explanations

references to varying degrees of crisis or challenging situations

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

ends

-0.19

endas

-0.17

enda

-0.17

andra

-0.16

ache

-0.16

endale

-0.16

eters

-0.16

esian

-0.16

itter

-0.15

age

-0.15

POSITIVE LOGITS

ally

0.32

ality

0.23

als

0.22

nal

0.20

 circumstances

0.19

naire

0.19

nement

0.19

quo

0.18

oji

0.18

alist

0.18

Activations Density 0.041%

references to varying degrees of crisis or challenging situations

No Comments

No Known Activations