INDEX

Explanations

references to social class and elite status

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

atters

-0.16

ĤŃ

-0.15

ra

-0.15

ral

-0.15

 AppState

-0.14

acements

-0.14

 journey

-0.14

requete

-0.14

 dept

-0.14

illion

-0.13

POSITIVE LOGITS

éĺ¶

0.18

 Bris

0.18

 cá»©u

0.16

 tastes

0.16

Fraction

0.15

 spons

0.15

éļİ

0.14

/exec

0.14

oplayer

0.14

 vá»įng

0.14

Activations Density 0.066%

references to social class and elite status

No Comments

No Known Activations