INDEX

Explanations

references to data handling and operations in coding contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ann

-0.16

 import

-0.16

ebek

-0.15

ree

-0.15

/we

-0.14

mon

-0.14

(s

-0.14

pro

-0.14

ander

-0.14

lette

-0.14

POSITIVE LOGITS

Ð¾ÑĢÐ¾ÑĤ

0.16

alley

0.16

ARRANT

0.15

ÂŃi

0.15

yen

0.15

dl

0.15

íĳľ

0.15

 onDataChange

0.15

iments

0.15

ccion

0.15

Activations Density 0.111%

references to data handling and operations in coding contexts

No Comments

No Known Activations