INDEX

Explanations

phrases that express an understanding or logical coherence of concepts

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

 sharedInstance

-0.18

ientos

-0.16

ogui

-0.16

 INCIDENTAL

-0.15

rava

-0.14

stered

-0.14

anship

-0.14

ots

-0.14

rio

-0.14

edb

-0.14

POSITIVE LOGITS

nar

0.16

éĢ

0.15

\modules

0.15

aira

0.14

ersed

0.14

 AÃ§

0.14

vais

0.14

 sense

0.14

sense

0.14

fully

0.14

Activations Density 0.011%

phrases that express an understanding or logical coherence of concepts

No Comments

No Known Activations