INDEX

Explanations

references to organized groupings of items or works, particularly in the context of collections or compilations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ieri

-0.15

ur

-0.15

raud

-0.14

itou

-0.14

orean

-0.14

 è¶

-0.14

ovol

-0.13

 manifest

-0.13

 Hlav

-0.13

bow

-0.13

POSITIVE LOGITS

kle

0.16

vÃ¡l

0.14

yn

0.14

erial

0.14

 Below

0.13

ebek

0.13

ee

0.13

-col

0.13

-piece

0.13

AtIndex

0.13

Activations Density 0.014%

references to organized groupings of items or works, particularly in the context of collections or compilations

No Comments

No Known Activations