INDEX

Explanations

abbreviations or shorthand forms of expressions involving "FY" and other terms related to familiarity or notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ping

-0.19

ni

-0.18

pin

-0.18

sto

-0.18

party

-0.18

pol

-0.18

pa

-0.18

leg

-0.17

pu

-0.17

POSITIVE LOGITS

ssel

0.23

draulic

0.22

outube

0.20

giene

0.20

draul

0.20

dney

0.19

lation

0.19

topl

0.19

ewitness

0.19

esterday

0.18

Activations Density 0.066%

abbreviations or shorthand forms of expressions involving "FY" and other terms related to familiarity or notation

No Comments

No Known Activations