INDEX

Explanations

references to deceit or misinformation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

Lah

-0.16

_RC

-0.15

elles

-0.14

Ø±Ø©

-0.14

ellas

-0.14

 spir

-0.14

ka

-0.14

 Alien

-0.14

ikh

-0.14

 Genuine

-0.14

POSITIVE LOGITS

-wsj

0.16

.heroku

0.15

ruby

0.15

/WebAPI

0.15

true

0.15

adem

0.15

aucoup

0.14

/vnd

0.14

 true

0.14

ennen

0.14

Activations Density 0.228%

references to deceit or misinformation

No Comments

No Known Activations