INDEX

Explanations

phrases indicating the conclusion or end of events or periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 late

-0.17

china

-0.15

æĹ©

-0.15

 early

-0.15

late

-0.15

 Begin

-0.15

igen

-0.14

ëª

-0.14

 Late

-0.14

 begin

-0.14

POSITIVE LOGITS

 tunnel

0.20

 tether

0.18

 term

0.17

unnel

0.17

usra

0.16

 tunnels

0.16

 Tunnel

0.16

 each

0.16

 innocence

0.15

 month

0.15

Activations Density 0.062%

phrases indicating the conclusion or end of events or periods

No Comments

No Known Activations