INDEX

Explanations

references to "House of" and similar phrases or titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 èµ¤

-0.17

enez

-0.16

ilet

-0.16

resh

-0.15

rello

-0.15

zzo

-0.15

baru

-0.14

vier

-0.14

rame

-0.14

koa

-0.14

POSITIVE LOGITS

 Representatives

0.21

 House

0.20

 house

0.17

 representatives

0.16

 Commons

0.16

oldem

0.15

/ws

0.15

_taken

0.15

 cards

0.15

 commons

0.15

Activations Density 0.014%

references to "House of" and similar phrases or titles

No Comments

No Known Activations