INDEX

Explanations

specific statistics and performance metrics related to a subject, particularly in a business or marketing context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

istrat

-0.16

etto

-0.16

igi

-0.15

 Andersen

-0.15

Æ¯

-0.14

rak

-0.14

Luc

-0.14

Ð¾Ð¾Ð±ÑĢÐ°Ð·

-0.14

Ð¼Ñĭ

-0.13

izzle

-0.13

POSITIVE LOGITS

emento

0.19

itom

0.15

ived

0.15

Roe

0.15

vely

0.15

plies

0.14

.volley

0.14

 nackte

0.14

pter

0.14

phem

0.14

Activations Density 0.135%

specific statistics and performance metrics related to a subject, particularly in a business or marketing context

No Comments

No Known Activations