INDEX

Explanations

elements indicating fictional content and disclaimers about the accuracy of information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

alles

-0.15

fty

-0.15

occo

-0.15

utsch

-0.14

rary

-0.14

ennie

-0.14

van

-0.13

ateurs

-0.13

dl

-0.13

akes

-0.13

POSITIVE LOGITS

undle

0.14

/gtest

0.14

_iff

0.14

ublic

0.13

ãĥ³ãĥĪ

0.13

à¥ĩà¤Ĺ

0.13

_$

0.13

 NONINFRINGEMENT

0.13

ãĥ³ãĥģ

0.13

izar

0.12

Activations Density 0.020%

elements indicating fictional content and disclaimers about the accuracy of information

No Comments

No Known Activations