INDEX

Explanations

questions and inquiries about data and understanding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

atos

-0.18

angler

-0.15

ÎĳÎĽ

-0.15

 spect

-0.14

ÐĴÐ¡

-0.14

ostel

-0.14

lsi

-0.14

ACION

-0.14

ãģĵãģ¡ãĤī

-0.14

æĹ¢çĦ¶

-0.14

POSITIVE LOGITS

 list

0.17

 Fowler

0.16

 anyone

0.16

 probably

0.15

list

0.15

 would

0.15

anye

0.15

ä¼į

0.15

Activations Density 0.115%

questions and inquiries about data and understanding

No Comments

No Known Activations