INDEX

Explanations

patterns related to method or property access 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 @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

áº¡ch

-0.19

ãĥ¼ãĥľ

-0.16

idel

-0.15

LPARAM

-0.15

ÏħÏĥ

-0.15

ÑĩÐ¸Ð¼

-0.15

Å¡ak

-0.15

Ð»ÑĥÑĪ

-0.14

opsy

-0.14

?url

-0.14

POSITIVE LOGITS

assy

0.17

 increment

0.16

 atom

0.15

ritz

0.14

 Atom

0.14

 hast

0.14

 console

0.14

 discern

0.14

un

0.14

ible

0.14

Activations Density 0.018%

patterns related to method or property access in a programming context

No Comments

No Known Activations