INDEX

Explanations

references to fear and related emotional concepts

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

quirer

-0.15

kers

-0.15

elib

-0.14

mÃ®

-0.14

arian

-0.14

arians

-0.14

umerator

-0.14

esto

-0.14

esa

-0.14

(rawValue

-0.13

POSITIVE LOGITS

fulness

0.34

mong

0.33

fully

0.33

lessly

0.32

 hÃ£

0.30

 mong

0.25

ful

0.24

lessness

0.24

full

0.23

 tactics

0.21

Activations Density 0.035%

references to fear and related emotional concepts

No Comments

No Known Activations

references to fear and related emotional concepts

No Comments

No Known Activations