INDEX

Explanations

technical terms related to programming and software components

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

undry

-0.15

aug

-0.15

opis

-0.14

cheon

-0.14

.NULL

-0.14

ÏĥÏħ

-0.14

anÃ¡

-0.13

Marsh

-0.13

 UIBar

-0.13

ibo

-0.13

POSITIVE LOGITS

 SvÄĽt

0.15

arte

0.15

Bes

0.15

adier

0.14

kit

0.14

ardy

0.14

nish

0.14

pler

0.14

ider

0.13

 belt

0.13

Activations Density 0.014%

technical terms related to programming and software components

No Comments

No Known Activations