INDEX

Explanations

mathematical terms and formulations related to limits, equations, and proofs in a structured context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

eyh

-0.16

porter

-0.16

ingu

-0.16

APTER

-0.15

atre

-0.15

erable

-0.14

ardown

-0.14

erge

-0.14

ommen

-0.14

roperties

-0.13

POSITIVE LOGITS

.paper

0.17

 beans

0.14

 Apple

0.14

apple

0.14

çĽ®ãĤĴ

0.14

iq

0.14

oor

0.14

 Courtney

0.14

alsa

0.13

Activations Density 0.166%

mathematical terms and formulations related to limits, equations, and proofs in a structured context

No Comments

No Known Activations