INDEX

Explanations

occurrences of the letter 'R' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

adius

-0.25

untime

-0.22

andom

-0.21

udy

-0.20

aise

-0.20

ounds

-0.19

adio

-0.19

adeon

-0.18

ange

-0.18

icht

-0.17

POSITIVE LOGITS

ramework

0.17

otor

0.17

iom

0.16

iw

0.16

quiv

0.15

ectors

0.15

rani

0.15

YA

0.15

inder

0.15

yal

0.14

Activations Density 0.041%

occurrences of the letter 'R' in various contexts

No Comments

No Known Activations