INDEX

Explanations

references to mental health issues and personal relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

å·§

-0.17

Ã¼le

-0.15

arov

-0.15

 Werner

-0.14

Ð·Ð½Ð°ÑĩÐ°

-0.14

('__

-0.14

LinkId

-0.14

ethnic

-0.13

arrera

-0.13

çłĤ

-0.13

POSITIVE LOGITS

 writing

0.19

 correspond

0.17

 publishing

0.16

 corres

0.15

 letters

0.15

 publishers

0.15

 publication

0.14

ctic

0.14

 Writing

0.14

 lifelong

0.14

Activations Density 0.068%

references to mental health issues and personal relationships

No Comments

No Known Activations