INDEX

Explanations

mentions of binary data and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

-0.17

.pp

-0.16

uppy

-0.16

Unc

-0.15

alon

-0.15

anova

-0.15

wards

-0.14

ible

-0.14

dm

-0.14

avr

-0.14

POSITIVE LOGITS

_crossentropy

0.23

/octet

0.23

ocular

0.22

 Laden

0.20

omial

0.20

SearchTree

0.19

-coded

0.18

/oct

0.18

ity

0.18

ized

0.17

Activations Density 0.013%

mentions of binary data and related concepts

No Comments

No Known Activations