INDEX

Explanations

mathematical expressions and equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

Dud

-0.15

 consistency

-0.15

enstein

-0.15

entina

-0.14

 consistent

-0.14

 eyed

-0.14

ãĥ³ãĤ¹

-0.13

 inconsistency

-0.13

ubar

-0.13

-chain

-0.13

POSITIVE LOGITS

UTO

0.15

 LPARAM

0.15

iver

0.15

ë¨¼

0.15

ãĤ¡

0.14

Å¡ek

0.14

oris

0.13

cks

0.13

áº¯c

0.13

aron

0.13

Activations Density 0.024%

mathematical expressions and equations

No Comments

No Known Activations