INDEX

Explanations

modal verbs indicating potential outcomes or future actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 reportedly

-0.15

 Seems

-0.15

riad

-0.15

Ã¡li

-0.14

 seems

-0.14

oret

-0.14

loat

-0.14

 Krish

-0.14

ÃĹ↵↵

-0.14

ldr

-0.14

POSITIVE LOGITS

 eventually

0.23

 somehow

0.23

 indeed

0.22

 soon

0.20

 ultimately

0.20

 eventual

0.18

 ÙĪØ£ÙĨ

0.17

 Eventually

0.17

soon

0.16

 forthcoming

0.15

Activations Density 0.187%

modal verbs indicating potential outcomes or future actions

No Comments

No Known Activations