INDEX

Explanations

references to educational or professional backgrounds

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

arya

-0.17

FK

-0.17

 Giang

-0.16

lyph

-0.16

 Hughes

-0.16

Hugh

-0.16

-0.15

 Lena

-0.15

POSITIVE LOGITS

 Justin

1.00

Justin

0.92

 Bieber

0.48

ustin

0.40

 justice

0.29

JT

0.27

 unjust

0.27

JIT

0.27

 Trudeau

0.27

 Justice

0.26

Activations Density 0.007%

references to educational or professional backgrounds

No Comments

No Known Activations