INDEX

Explanations

publication-related metadata and citation information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

hol

-0.19

culus

-0.16

nam

-0.15

hol

-0.15

om

-0.15

ouch

-0.15

omi

-0.14

è¦ĸ

-0.14

consult

-0.14

idual

-0.13

POSITIVE LOGITS

mgr

0.14

ungen

0.14

imli

0.13

gger

0.13

ï»¿#

0.13

ambi

0.13

iego

0.13

uisse

0.13

OrElse

0.13

Activations Density 0.010%

publication-related metadata and citation information

No Comments

No Known Activations