INDEX

Explanations

elements describing physical processes or states, particularly related to cooking or chemistry

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

reso

-0.15

 Rhino

-0.14

embre

-0.13

rov

-0.13

idak

-0.13

adero

-0.13

ipers

-0.13

 PureComponent

-0.13

 dumpster

-0.12

.AddComponent

-0.12

POSITIVE LOGITS

 bubbles

0.49

 foam

0.47

 bubble

0.44

 Foam

0.40

fo

0.40

 bubb

0.38

bubble

0.38

æ³¡

0.38

 Bubble

0.36

fro

0.36

Activations Density 0.037%

elements describing physical processes or states, particularly related to cooking or chemistry

No Comments

No Known Activations