INDEX

Explanations

terms related to props and their usages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

catid

-0.15

 comb

-0.15

resse

-0.15

wich

-0.15

ered

-0.15

ãģĿ

-0.15

istrat

-0.14

erk

-0.14

indre

-0.14

+</

-0.14

POSITIVE LOGITS

 Prop

0.16

daily

0.14

 PROP

0.14

 daily

0.14

rawl

0.14

sun

0.14

ahi

0.14

agate

0.14

osition

0.14

Activations Density 0.029%

terms related to props and their usages

No Comments

No Known Activations