INDEX

Explanations

references to health officials and governmental roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

å½

-0.18

oki

-0.16

 transit

-0.15

 Transit

-0.14

 Maul

-0.14

prox

-0.14

OU

-0.14

åĲ¾

-0.13

uitka

-0.13

.Automation

-0.13

POSITIVE LOGITS

 Alley

0.18

enville

0.17

 Pers

0.16

cin

0.15

avern

0.15

ifa

0.15

vaz

0.15

fy

0.15

 pers

0.15

ernal

0.14

Activations Density 0.031%

references to health officials and governmental roles

No Comments

No Known Activations