INDEX

Explanations

terms related to optimization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

led

-0.15

leton

-0.15

les

-0.15

rp

-0.15

ÏĢÎ®

-0.14

iente

-0.14

lesi

-0.14

hound

-0.14

uela

-0.14

 Lair

-0.14

POSITIVE LOGITS

imal

0.25

imum

0.23

-out

0.20

-outs

0.19

ima

0.19

/opt

0.18

IMAL

0.18

³

0.18

opt

0.18

-Out

0.18

Activations Density 0.014%

terms related to optimization

No Comments

No Known Activations