INDEX

Explanations

references to government officials and their titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

tures

-0.15

erspective

-0.15

utz

-0.15

ilt

-0.15

-0.14

Ð»Ð¸ÑĨ

-0.14

ics

-0.14

SSIP

-0.14

idas

-0.14

uke

-0.14

POSITIVE LOGITS

-General

0.25

ariat

0.23

-general

0.23

aries

0.20

 secretary

0.19

-secret

0.19

ship

0.19

arial

0.18

retry

0.18

 Secretary

0.16

Activations Density 0.013%

references to government officials and their titles

No Comments

No Known Activations