INDEX

Explanations

mathematical operations and transformations within equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

_rewrite

-0.16

isko

-0.15

esel

-0.15

sko

-0.15

edla

-0.15

ãĤ¦ãĥĪ

-0.15

edir

-0.14

anzi

-0.14

ensation

-0.14

uzzi

-0.14

POSITIVE LOGITS

ä¸Ģä¸ĭ

0.15

 bottoms

0.15

 bottom

0.14

otle

0.14

ä¹ī

0.14

urname

0.14

 Bottom

0.14

Activations Density 0.113%

mathematical operations and transformations within equations

No Comments

No Known Activations