INDEX

Explanations

punctuation marks and ellipses

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

ercial

-0.16

 machine

-0.15

ighter

-0.15

unker

-0.15

-0.14

POSITIVE LOGITS

 bÃ²

0.17

DEX

0.16

 magn

0.14

-Ta

0.14

/resource

0.14

 Pearce

0.14

amburger

0.14

 æ°ĳ

0.14

URLException

0.14

UrlParser

0.14

Activations Density 0.002%

punctuation marks and ellipses

No Comments

No Known Activations