INDEX

Explanations

comments or annotations in text, particularly in programming or markup contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

uto

-0.16

Ã¡ch

-0.15

io

-0.15

uro

-0.14

oft

-0.14

akk

-0.14

ISA

-0.13

ÑĪÐ¸Ð»Ð°

-0.13

Ã¤n

-0.13

Î²Î¬Î»

-0.13

POSITIVE LOGITS

Gow

0.15

acco

0.15

otte

0.15

ãĥ³ãĥī

0.14

ë²Į

0.14

Ð¾Ð±Ð¾Ð²

0.14

ycz

0.14

alker

0.14

 moder

0.14

bote

0.14

Activations Density 0.021%

comments or annotations in text, particularly in programming or markup contexts

No Comments

No Known Activations