INDEX

Explanations

references to natural landscapes and environmental features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

alue

-0.17

áº¡ch

-0.15

ctl

-0.15

 apprentices

-0.14

ãģŁãģĹ

-0.14

atab

-0.14

rad

-0.14

 ÐłÐ°Ð´

-0.14

 Beaver

-0.14

ree

-0.13

POSITIVE LOGITS

mar

0.16

Abstract

0.15

 spoon

0.14

 Abstract

0.14

interop

0.14

undi

0.14

wear

0.14

rouch

0.14

msp

0.13

forget

0.13

Activations Density 0.552%

references to natural landscapes and environmental features

No Comments

No Known Activations