INDEX

Explanations

references to programming elements and frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 previews

-0.16

agree

-0.15

izzard

-0.15

meni

-0.15

emic

-0.15

SupportActionBar

-0.14

bra

-0.14

ÑĢÑĸÑĩ

-0.14

Ð½ÑĸÐ²

-0.14

isu

-0.14

POSITIVE LOGITS

ieved

0.17

rod

0.15

 tack

0.15

ernen

0.14

 Gron

0.14

kit

0.14

ActiveSheet

0.14

eroon

0.14

alm

0.14

 Schwarz

0.13

Activations Density 0.003%

references to programming elements and frameworks

No Comments

No Known Activations