INDEX

Explanations

terms related to education and professional qualifications, especially in law and academia

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ensch

-0.17

amm

-0.16

 Morr

-0.16

vak

-0.15

ammer

-0.15

udas

-0.14

ibri

-0.14

yst

-0.14

 militar

-0.14

yster

-0.14

POSITIVE LOGITS

etchup

0.15

ÐµÐ½Ð·

0.15

ervo

0.15

uevo

0.15

iana

0.14

ngo

0.14

-meta

0.14

atown

0.14

ê²°

0.14

olta

0.14

Activations Density 0.610%

terms related to education and professional qualifications, especially in law and academia

No Comments

No Known Activations