INDEX

Explanations

key phrases related to options and experiences in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 everywhere

-0.18

ÄįÃ¡st

-0.16

 Everywhere

-0.14

ogie

-0.14

iki

-0.14

['-

-0.14

 Libert

-0.13

 better

-0.13

 Better

-0.13

hem

-0.13

POSITIVE LOGITS

higher

0.19

 higher

0.18

Higher

0.17

 increasingly

0.17

pretty

0.17

/latest

0.17

 upper

0.16

PRETTY

0.16

 Higher

0.16

 ultimately

0.16

Activations Density 0.011%

key phrases related to options and experiences in various contexts

No Comments

No Known Activations