INDEX

Explanations

references to "respect" and its variations within the context of various topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

opa

-0.17

><![

-0.16

hell

-0.15

rogen

-0.14

nul

-0.14

iated

-0.14

ish

-0.14

Roz

-0.14

pu

-0.14

POSITIVE LOGITS

 regard

0.21

ToBounds

0.20

 regards

0.20

 respect

0.17

stral

0.16

æĸ¼

0.15

oins

0.15

orno

0.15

ensex

0.15

pecially

0.14

Activations Density 0.025%

references to "respect" and its variations within the context of various topics

No Comments

No Known Activations