INDEX

Explanations

phrases related to product features and functionalities

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

-0.14

usk

-0.14

opr

-0.14

czy

-0.13

born

-0.13

upa

-0.13

ikki

-0.13

INED

-0.13

ick

-0.12

ìłĦ

-0.12

POSITIVE LOGITS

angstrom

0.17

elan

0.14

ìĿ´íĦ°

0.14

engu

0.14

 itemprop

0.14

_argument

0.13

',['../

0.13

å¹ħ

0.13

_representation

0.13

.updateDynamic

0.13

Activations Density 0.254%

phrases related to product features and functionalities

No Comments

No Known Activations

phrases related to product features and functionalities

No Comments

No Known Activations