INDEX

Explanations

words related to concepts of awareness and understanding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

agli

-0.15

agem

-0.15

ãĥĶãĥ¼

-0.15

 Alta

-0.14

yla

-0.14

coli

-0.14

mentions

-0.14

cket

-0.13

ensch

-0.13

paren

-0.13

POSITIVE LOGITS

Ign

0.24

oring

0.23

acio

0.23

ition

0.22

orer

0.22

ite

0.21

eous

0.20

azio

0.20

ored

0.20

orable

0.20

Activations Density 0.017%

words related to concepts of awareness and understanding

No Comments

No Known Activations