INDEX

Explanations

references to allegations and accusations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

upt

-0.16

icens

-0.16

angler

-0.15

ehler

-0.15

anik

-0.15

lsi

-0.14

support

-0.14

roe

-0.14

ality

-0.14

dependent

-0.14

POSITIVE LOGITS

#echo

0.17

 Moon

0.16

 moon

0.14

ÙĥÙĩ

0.14

moon

0.14

.WinForms

0.14

/assert

0.13

/problem

0.13

/request

0.13

Activations Density 0.031%

references to allegations and accusations

No Comments

No Known Activations