INDEX

Explanations

references to in-person interactions and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çĲ´

-0.15

 hlav

-0.14

izio

-0.14

cbd

-0.14

ippet

-0.13

reira

-0.13

ights

-0.13

asil

-0.13

getti

-0.13

ÐµÐºÑĤÐ¾ÑĢÐ°

-0.13

POSITIVE LOGITS

 face

0.60

 physical

0.53

 physically

0.48

face

0.47

physical

0.46

-face

0.45

 personally

0.45

 person

0.44

 Face

0.44

 Physical

0.42

Activations Density 0.297%

references to in-person interactions and experiences

No Comments

No Known Activations