INDEX

Explanations

references to academic disciplines and fields of study

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

Ð±Ð¾ÑĢ

-0.17

 dáº¥u

-0.15

ubat

-0.15

ourg

-0.15

amework

-0.14

eyen

-0.14

uguay

-0.14

umbn

-0.14

phe

-0.14

.tt

-0.14

POSITIVE LOGITS

alon

0.20

 department

0.19

 Department

0.16

.department

0.16

0.15

/vector

0.14

 departments

0.14

dept

0.14

 dept

0.14

Activations Density 0.136%

references to academic disciplines and fields of study

No Comments

No Known Activations