INDEX

Explanations

phrases indicating possession or existence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

imen

-0.15

Ð»Ð°Ñĩ

-0.15

eb

-0.15

ãĤıãģĳ

-0.14

EDIA

-0.14

 Pearce

-0.13

unu

-0.13

à¹Īà¸²à¸¢

-0.12

ìį¨

-0.12

POSITIVE LOGITS

ustry

0.16

 dela

0.14

htag

0.14

 Sorting

0.14

ais

0.14

quia

0.14

á»§ng

0.14

htub

0.14

AGO

0.14

.TIM

0.13

Activations Density 0.235%

phrases indicating possession or existence

No Comments

No Known Activations

phrases indicating possession or existence

No Comments

No Known Activations