INDEX

Explanations

instances of the abbreviation "S."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ffe

-0.19

erialize

-0.17

eum

-0.16

gnore

-0.16

ttp

-0.15

tml

-0.15

irtual

-0.15

TEGER

-0.14

 continuity

-0.14

POSITIVE LOGITS

uper

0.26

ecure

0.24

ever

0.24

pecific

0.23

chool

0.23

quare

0.23

elf

0.22

upported

0.22

mart

0.22

ocial

0.22

Activations Density 0.008%

instances of the abbreviation "S."

No Comments

No Known Activations