INDEX

Explanations

phrases related to data classification and selection criteria

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ernote

-0.17

olla

-0.17

odesk

-0.15

echan

-0.15

ossa

-0.15

ajs

-0.15

ductor

-0.14

avanaugh

-0.14

istor

-0.14

olia

-0.14

POSITIVE LOGITS

ulty

0.16

 vice

0.15

 Ð¿Ð¾Ð´Ð²

0.15

 type

0.14

 occasion

0.14

FromArray

0.14

 chá»§

0.14

aec

0.13

 Bret

0.13

Activations Density 0.255%

phrases related to data classification and selection criteria

No Comments

No Known Activations