INDEX

Explanations

references to scholarly articles and publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

$MESS

-0.18

ltk

-0.15

LEGRO

-0.14

icont

-0.14

round

-0.14

ssf

-0.14

Ãºi

-0.14

olland

-0.13

_userdata

-0.13

.bid

-0.13

POSITIVE LOGITS

IZER

0.15

ijken

0.15

µ

0.15

STER

0.15

uw

0.14

arna

0.14

 Arms

0.14

cci

0.14

 Proceed

0.13

agna

0.13

Activations Density 0.004%

references to scholarly articles and publications

No Comments

No Known Activations