INDEX

Explanations

mentions and discussions related to fuel and its efficiency

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

es

-0.19

est

-0.19

esting

-0.15

fy

-0.15

unto

-0.15

ew

-0.15

ect

-0.14

kova

-0.14

epy

-0.14

lim

-0.14

POSITIVE LOGITS

led

0.35

ing

0.23

ING

0.19

ë¡ľëĬĶ

0.18

ë¡ľ

0.18

erken

0.17

issen

0.17

lem

0.17

LED

0.17

ingu

0.16

Activations Density 0.014%

mentions and discussions related to fuel and its efficiency

No Comments

No Known Activations