INDEX

Explanations

references to names and their significance 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 @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 Loader

-0.14

assin

-0.14

pto

-0.14

istes

-0.14

ente

-0.14

 elevated

-0.14

inae

-0.14

zahl

-0.14

peater

-0.13

POSITIVE LOGITS

plate

0.22

plates

0.20

åı¤å±ĭ

0.18

cheap

0.16

verity

0.16

ake

0.15

istrovstvÃŃ

0.15

addon

0.15

adesh

0.14

-brand

0.14

Activations Density 0.056%

references to names and their significance in various contexts

No Comments

No Known Activations