INDEX

Explanations

references to programming constructs, particularly related to structure and definitions in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

tml

-0.18

cket

-0.15

 à¤²à¤Ĺà¤¤

-0.14

rgan

-0.14

swick

-0.13

 Oliv

-0.13

bos

-0.13

 exper

-0.13

ment

-0.13

ÐµÑĤÐ¾Ð¼

-0.13

POSITIVE LOGITS

Ł

0.15

ohon

0.15

atomy

0.15

.tp

0.14

(exports

0.13

/Foundation

0.13

@gmail

0.12

exus

0.12

uiltin

0.12

Activations Density 0.104%

references to programming constructs, particularly related to structure and definitions in code

No Comments

No Known Activations