INDEX

Explanations

terms related to manipulation and control in societal contexts

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

elper

-0.16

taire

-0.15

aro

-0.15

Mus

-0.15

zej

-0.15

pter

-0.14

ÑĤÑı

-0.14

kle

-0.14

inesis

-0.14

éĢĢ

-0.14

POSITIVE LOGITS

 brain

0.44

 Brain

0.41

brain

0.40

Brain

0.38

 brains

0.28

èĦĳ

0.25

 programming

0.23

èħ¦

0.23

 Programming

0.22

programming

0.22

Activations Density 0.011%

terms related to manipulation and control in societal contexts

No Comments

No Known Activations

terms related to manipulation and control in societal contexts

No Comments

No Known Activations