INDEX

Explanations

instances of the word "decided" and track its variations to identify decision-making contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

anÃ¡

-0.18

vos

-0.15

eldo

-0.15

lac

-0.15

ipa

-0.15

Ã©o

-0.15

odal

-0.15

uggestions

-0.15

rede

-0.15

atk

-0.14

POSITIVE LOGITS

 against

0.24

 upon

0.24

against

0.21

 Against

0.21

Against

0.20

upon

0.20

 Upon

0.18

Upon

0.17

naire

0.17

 rather

0.16

Activations Density 0.027%

instances of the word "decided" and track its variations to identify decision-making contexts

No Comments

No Known Activations