INDEX

Explanations

references to processes, events, or milestones

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ÑĩÐ¸Ñħ

-0.17

ãģĴ

-0.15

ves

-0.15

ollider

-0.15

vers

-0.14

Ð¾Ð³ÑĢÐ°ÑĦÐ¸Ñı

-0.14

 Kauf

-0.14

isse

-0.14

åıį

-0.14

ra

-0.14

POSITIVE LOGITS

ocrine

0.17

 behalf

0.15

arel

0.15

Ãºn

0.15

âĢ¦↵↵↵

0.15

marshall

0.14

 vá»įng

0.14

apest

0.14

 ----------------------------------------------------------------------------

0.14

mn

0.14

Activations Density 0.215%

references to processes, events, or milestones

No Comments

No Known Activations