INDEX

Explanations

terms related to pseudo-elements and pseudo-classes in programming or web development contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ãĥ©ãĥĥãĤ¯

-0.17

flo

-0.16

evity

-0.15

itti

-0.15

ybrid

-0.14

uteur

-0.14

ombo

-0.14

/fw

-0.14

orio

-0.14

ollo

-0.14

POSITIVE LOGITS

ocode

0.18

onyms

0.18

ovÄĽ

0.17

onym

0.17

onymous

0.17

 pseudo

0.17

 pseud

0.16

§

0.15

-random

0.15

odo

0.15

Activations Density 0.007%

terms related to pseudo-elements and pseudo-classes in programming or web development contexts

No Comments

No Known Activations