INDEX

Explanations

terms related to acceleration and its derivatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

soever

-0.18

ills

-0.16

zzle

-0.15

RIES

-0.15

akes

-0.15

lands

-0.15

ahi

-0.14

aking

-0.14

ild

-0.14

ongoose

-0.14

POSITIVE LOGITS

/de

0.21

ometer

0.17

ometers

0.17

idious

0.17

avier

0.16

Ø¯Ùĩ

0.16

ial

0.16

ando

0.15

idia

0.15

lico

0.15

Activations Density 0.017%

terms related to acceleration and its derivatives

No Comments

No Known Activations