INDEX

Explanations

references to fans and their engagement or feelings towards a show or event

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ronics

-0.17

raya

-0.17

 fark

-0.15

undy

-0.15

uce

-0.14

itsu

-0.14

à¹Ĥà¸¢

-0.14

hazi

-0.14

çĦ

-0.14

Ã§on

-0.14

POSITIVE LOGITS

 demand

0.19

 familiar

0.17

 flock

0.17

 demands

0.16

can

0.16

 Shepard

0.16

 voted

0.16

Vor

0.16

demand

0.15

Activations Density 0.087%

references to fans and their engagement or feelings towards a show or event

No Comments

No Known Activations