INDEX

Explanations

discussions around performance metrics and public reception in the entertainment industry

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

iti

-0.15

 Kramer

-0.15

 Profile

-0.14

tere

-0.14

esy

-0.14

ansi

-0.14

iverz

-0.13

ajes

-0.13

ToLocal

-0.13

 cres

-0.13

POSITIVE LOGITS

oji

0.16

ates

0.15

 Steel

0.15

MLA

0.14

PLL

0.14

 devuelve

0.14

gia

0.14

 contextual

0.14

 Cargo

0.14

able

0.13

Activations Density 0.221%

discussions around performance metrics and public reception in the entertainment industry

No Comments

No Known Activations