INDEX

Explanations

lines of code related to user interface interactions in a programming context

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

\<

-0.15

 Lobby

-0.14

&=

-0.14

aug

-0.14

#:

-0.14

ikler

-0.14

chor

-0.13

oret

-0.13

iry

-0.13

olog

-0.13

POSITIVE LOGITS

mani

0.16

erti

0.16

ÑĢÐ¾Ð³

0.16

resas

0.15

OUTH

0.15

ropol

0.15

ameda

0.15

resa

0.14

ALSE

0.14

ces

0.14

Activations Density 0.206%

lines of code related to user interface interactions in a programming context

No Comments

No Known Activations