INDEX

Explanations

terms related to deep learning and neural networks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

-proxy

-0.16

xfd

-0.14

opause

-0.14

 Beard

-0.14

antee

-0.14

ampaign

-0.14

iland

-0.14

å²

-0.14

 Shepard

-0.13

DEX

-0.13

POSITIVE LOGITS

bid

0.26

 recurrent

0.25

Seq

0.24

(Seq

0.24

Bid

0.23

seq

0.23

 LSTM

0.22

 sequence

0.22

Bid

0.22

 Long

0.22

Activations Density 0.007%

terms related to deep learning and neural networks

No Comments

No Known Activations