INDEX

Explanations

proper names, particularly those of researchers and contributors in scientific publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

otte

-0.15

 rost

-0.15

dera

-0.15

awl

-0.14

etty

-0.14

raft

-0.14

arian

-0.13

 tarz

-0.13

 ÐºÐ°Ð»

-0.13

ophobia

-0.13

POSITIVE LOGITS

 conc

0.15

uede

0.15

ves

0.15

orean

0.14

ahoo

0.14

ij

0.14

ta

0.14

lesson

0.14

æĭ³

0.14

Thi

0.14

Activations Density 0.292%

proper names, particularly those of researchers and contributors in scientific publications

No Comments

No Known Activations