INDEX

Explanations

references to political actions and communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

isser

-0.17

.setOutput

-0.17

poz

-0.15

é½

-0.14

yect

-0.14

éĹ»

-0.13

izen

-0.13

poz

-0.13

Ð°ÑĢÑĤÐ°Ð¼

-0.13

 Macy

-0.13

POSITIVE LOGITS

MP

0.53

MP

0.42

mp

0.39

_MP

0.38

MPs

0.38

 Member

0.37

Mp

0.35

_mp

0.34

 Constit

0.32

 constituency

0.32

Activations Density 0.116%

references to political actions and communication

No Comments

No Known Activations