INDEX

Explanations

phrases that indicate societal or commercial stereotypes, especially related to cannabis and its consumers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 ëĶ°

-0.16

ift

-0.15

 TYPO

-0.14

][/

-0.14

UZ

-0.14

 Fuse

-0.14

éĥİ

-0.14

blr

-0.14

 Voll

-0.13

autoload

-0.13

POSITIVE LOGITS

Ð¾Ð½Ñĸ

0.16

'gc

0.16

opard

0.16

cter

0.15

iah

0.14

 cellForRowAt

0.14

kovi

0.14

 Remote

0.14

 terms

0.14

imple

0.14

Activations Density 0.325%

phrases that indicate societal or commercial stereotypes, especially related to cannabis and its consumers

No Comments

No Known Activations