INDEX

Explanations

proper names of individuals and notable figures

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

ires

-0.17

lak

-0.16

irc

-0.15

ierz

-0.14

jack

-0.14

beck

-0.14

RC

-0.14

 Notices

-0.14

ĺ

-0.14

 Boards

-0.14

POSITIVE LOGITS

elper

0.17

linky

0.15

rlen

0.15

elpers

0.15

UD

0.15

phe

0.14

ENU

0.14

@Setter

0.14

BOTTOM

0.14

Kah

0.14

Activations Density 0.030%

proper names of individuals and notable figures

No Comments

No Known Activations