INDEX

Explanations

terms related to regulatory and legal constraints in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

kop

-0.20

unos

-0.16

vak

-0.14

á»ķ

-0.14

 NSStringFromClass

-0.13

(æĹ¥

-0.13

'%"

-0.13

iggers

-0.13

'%$

-0.13

POSITIVE LOGITS

 even

0.17

 other

0.17

 merely

0.17

 specifically

0.17

ito

0.17

 simply

0.16

ason

0.16

 directly

0.16

lld

0.15

itto

0.15

Activations Density 0.334%

terms related to regulatory and legal constraints in various contexts

No Comments

No Known Activations