INDEX

Explanations

names of authors and contributors in academic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

afen

-0.15

.AI

-0.14

lei

-0.14

ooks

-0.14

aco

-0.14

aming

-0.13

åĬŁ

-0.13

ãģ»ãģ©

-0.13

ect

-0.13

thinkable

-0.13

POSITIVE LOGITS

Smooth

0.13

Ð¾Ð¿Ð°Ñģ

0.13

 Doyle

0.13

permanent

0.13

 Sexo

0.13

inÃ¡ÅĻ

0.12

 hiss

0.12

anja

0.12

 æĢ§

0.12

.getDrawable

0.12

Activations Density 0.011%

names of authors and contributors in academic contexts

No Comments

No Known Activations