INDEX

Explanations

function calls or method invocations in code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

aus

-0.16

Dud

-0.14

 Merk

-0.14

Normalization

-0.13

Î¾ÎµÎ¹

-0.13

angu

-0.13

compatible

-0.13

Ã¤Ã¤n

-0.13

stÃŃ

-0.13

egt

-0.13

POSITIVE LOGITS

èĭ

0.16

èĺ

0.15

//

0.15

ÐºÑĥÐ»

0.14

DRV

0.14

ullo

0.14

 rack

0.13

 cdecl

0.13

asso

0.13

anz

0.13

Activations Density 0.030%

function calls or method invocations in code snippets

No Comments

No Known Activations