INDEX

Explanations

URLs and references to academic and scientific articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ander

-0.15

agan

-0.15

utoff

-0.14

anta

-0.14

sak

-0.14

rollment

-0.14

enti

-0.14

nek

-0.13

à¸¢à¸§

-0.13

acht

-0.13

POSITIVE LOGITS

doi

0.20

ISS

0.18

doi

0.16

Err

0.16

ifact

0.15

DOI

0.14

 Else

0.14

jee

0.14

onya

0.13

do

0.13

Activations Density 0.030%

URLs and references to academic and scientific articles

No Comments

No Known Activations