INDEX

Explanations

references to authors and their perspectives on historical arguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

arkin

-0.14

elan

-0.14

HQ

-0.14

tered

-0.14

abinet

-0.13

lags

-0.13

_NC

-0.13

@(

-0.13

BY

-0.13

ered

-0.13

POSITIVE LOGITS

olars

0.15

taÅŁ

0.15

á»ķ

0.15

Sizer

0.13

ÐºÐ¾ÑĤ

0.13

olar

0.13

agr

0.13

mah

0.13

Activations Density 0.144%

references to authors and their perspectives on historical arguments

No Comments

No Known Activations