INDEX

Explanations

concepts involving dualities or oppositions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

åĨµ

-0.16

illac

-0.16

éĢ¸

-0.14

é¦Ļ

-0.13

à¥ĩà¤ª

-0.13

_rgba

-0.13

.hasNext

-0.13

plib

-0.13

RIPT

-0.13

emax

-0.13

POSITIVE LOGITS

 opposite

0.76

 reverse

0.60

 inverse

0.52

 Reverse

0.52

 oppos

0.50

reverse

0.50

åıį

0.49

Reverse

0.49

 reversed

0.49

inverse

0.45

Activations Density 0.276%

concepts involving dualities or oppositions in various contexts

No Comments

No Known Activations