INDEX

Explanations

technical terms and metrics related to data, programming, and product specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

igg

-0.16

WEEN

-0.15

:maj

-0.14

Lau

-0.14

kne

-0.14

Ø±ÛĮÚ©

-0.14

ilde

-0.14

andler

-0.13

 antig

-0.13

eb

-0.13

POSITIVE LOGITS

.asc

0.16

 HÃ¼s

0.15

 æĶ¿

0.14

celik

0.14

ãĤ¦ãĥ³

0.14

 Elias

0.13

Î¼Î®

0.13

ÏĢÏīÏĤ

0.13

 merged

0.13

.Mapping

0.13

Activations Density 0.541%

technical terms and metrics related to data, programming, and product specifications

No Comments

No Known Activations