INDEX

Explanations

phrases related to providing information and education

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

enger

-0.16

iff

-0.16

arr

-0.15

-inv

-0.15

itz

-0.15

ilet

-0.15

 Warner

-0.14

ogi

-0.14

Bry

-0.14

ãģĳãĤĮãģ°

-0.13

POSITIVE LOGITS

à¸±à¸Ļà¸ĺ

0.15

deme

0.15

Ø¨Ø³

0.14

agraph

0.14

ModelProperty

0.14

achen

0.14

ÐµÐ»ÑĮÐ·Ñı

0.14

mys

0.14

 ÑĥÐ¼Ð¾Ð²

0.14

 prelim

0.13

Activations Density 0.016%

phrases related to providing information and education

No Comments

No Known Activations