INDEX

Explanations

connections and relationships represented by numbers and mathematical models

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

aida

-0.15

iesel

-0.15

è§Ī

-0.14

amu

-0.14

 Reich

-0.13

arton

-0.13

echan

-0.13

á»ĩn

-0.13

iÄįe

-0.13

POSITIVE LOGITS

 represent

0.54

ä»£è¡¨

0.52

 represents

0.51

represent

0.51

 representing

0.50

è¡¨ç¤º

0.46

 Represent

0.44

 Represents

0.43

 representa

0.40

 reprÃ©s

0.40

Activations Density 0.455%

connections and relationships represented by numbers and mathematical models

No Comments

No Known Activations