INDEX

Explanations

descriptions of living spaces or accommodations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 æĳ

-0.15

 bout

-0.14

wright

-0.14

skyt

-0.14

idos

-0.14

vais

-0.14

 Campus

-0.14

smith

-0.13

_Lean

-0.13

åľĴ

-0.13

POSITIVE LOGITS

 living

0.21

living

0.18

INDER

0.17

 sleeping

0.17

 Living

0.16

Living

0.16

 Sleeping

0.16

 kitchen

0.15

licer

0.15

 Landing

0.15

Activations Density 0.099%

descriptions of living spaces or accommodations

No Comments

No Known Activations