INDEX

Explanations

punctuation marks and references to historical figures and warfare

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 McCart

-0.15

jes

-0.15

abaj

-0.15

ÙĦØ©

-0.15

reek

-0.15

 Marr

-0.14

 Traverse

-0.14

POSITIVE LOGITS

 rede

0.15

 Midlands

0.15

ĢìĿ´

0.15

anford

0.14

 blot

0.14

 Reagan

0.14

UnderTest

0.14

 Pound

0.14

çĽ

0.13

 Andersen

0.13

Activations Density 0.024%

punctuation marks and references to historical figures and warfare

No Comments

No Known Activations