INDEX

Explanations

technical terms and elements related to programming and software development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

.modules

-0.17

 blast

-0.15

antz

-0.14

ici

-0.14

 ÙħØ²

-0.14

 dÃ¶k

-0.14

antt

-0.13

ict

-0.13

ove

-0.13

odes

-0.13

POSITIVE LOGITS

chest

0.16

CRY

0.16

atoi

0.15

.COMP

0.15

ses

0.15

éı¡

0.15

ãĤ¤ãĥī

0.14

Ð²ÐµÑĢÐ¶

0.14

cobra

0.14

pei

0.13

Activations Density 0.002%

technical terms and elements related to programming and software development

No Comments

No Known Activations