INDEX

Explanations

terms related to architectural features and historical structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

-0.15

ilos

-0.15

azzi

-0.14

omin

-0.14

Column

-0.14

adera

-0.14

SHA

-0.14

opot

-0.13

ylie

-0.13

POSITIVE LOGITS

 medieval

0.22

 Medieval

0.19

 Norman

0.19

Norm

0.17

ilen

0.17

aight

0.17

Tud

0.16

 Antar

0.16

ryb

0.15

 Norm

0.15

Activations Density 0.011%

terms related to architectural features and historical structures

No Comments

No Known Activations