INDEX

Explanations

terms related to software licensing and usage permissions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 Durant

-0.16

etrain

-0.15

eteria

-0.15

mey

-0.15

isc

-0.15

ONO

-0.14

 setattr

-0.14

iesz

-0.14

olicit

-0.14

qus

-0.14

POSITIVE LOGITS

kas

0.19

-Origin

0.14

å¦¹

0.14

yleft

0.14

 WithEvents

0.14

ãĥ³ãĤ¬

0.14

à¸

0.14

lld

0.14

aea

0.14

-commercial

0.13

Activations Density 0.012%

terms related to software licensing and usage permissions

No Comments

No Known Activations