INDEX

Explanations

names and terms related to organizations 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 @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ÐµÑĩÐ½Ð¾

-0.16

reff

-0.16

esor

-0.16

agan

-0.15

UNT

-0.15

edl

-0.15

åł¡

-0.14

Builders

-0.14

ocator

-0.14

inp

-0.14

POSITIVE LOGITS

 founder

0.23

 president

0.20

 leader

0.20

 President

0.20

 director

0.19

 owner

0.18

 boss

0.18

 founding

0.18

 head

0.18

 employees

0.18

Activations Density 0.205%

names and terms related to organizations and education

No Comments

No Known Activations