INDEX

Explanations

references to Trump and his administration's policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

arges

-0.17

arton

-0.16

 parlament

-0.15

 nues

-0.15

 burg

-0.15

áº¡

-0.14

fts

-0.14

onse

-0.14

hop

-0.14

ãĤıãģĽ

-0.14

POSITIVE LOGITS

 executive

0.31

 Executive

0.29

Executive

0.26

 Trump

0.26

 rollback

0.23

 roll

0.23

 resc

0.23

exec

0.22

Trump

0.21

EO

0.21

Activations Density 0.148%

references to Trump and his administration's policies

No Comments

No Known Activations