INDEX

Explanations

variations of the word "fond" and expressions of affection or positive sentiment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

erre

-0.18

er

-0.17

erse

-0.16

edList

-0.16

erif

-0.15

ease

-0.15

bw

-0.15

orgot

-0.14

orsch

-0.14

erken

-0.14

POSITIVE LOGITS

ue

0.22

amental

0.20

ness

0.19

icher

0.17

sb

0.17

ly

0.17

ÄĽlÃŃ

0.17

ensation

0.16

.GroupLayout

0.16

 fond

0.16

Activations Density 0.011%

variations of the word "fond" and expressions of affection or positive sentiment

No Comments

No Known Activations