INDEX

Explanations

concepts related to fairness, accountability, and the ethical treatment of individuals 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 @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ITTE

-0.15

Nev

-0.14

ÅĽmy

-0.14

onders

-0.14

YPE

-0.14

ctype

-0.14

PU

-0.14

oÄį

-0.13

 Ø¯Ø³ØªÛĮ

-0.13

POSITIVE LOGITS

ness

0.29

 enough

0.20

NESS

0.19

(er

0.19

lest

0.18

 Enough

0.18

ä¸Ķ

0.17

way

0.17

 ÅŁekilde

0.17

,strong

0.16

Activations Density 0.297%

concepts related to fairness, accountability, and the ethical treatment of individuals in various contexts

No Comments

No Known Activations