INDEX

Explanations

references to various types of documents and their properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

fall

-0.14

athe

-0.14

Beg

-0.14

 mainland

-0.14

çĹ

-0.14

Pla

-0.13

istol

-0.13

wards

-0.13

otta

-0.13

alytics

-0.13

POSITIVE LOGITS

efon

0.17

ãĥ¥

0.16

afil

0.16

interop

0.15

pez

0.15

MBER

0.15

obo

0.15

etur

0.14

çļ

0.14

baz

0.14

Activations Density 0.035%

references to various types of documents and their properties

No Comments

No Known Activations