INDEX

Explanations

occurrences of speeches or addresses made to groups or assemblies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

byt

-0.15

ekil

-0.15

-LAST

-0.14

 Kear

-0.14

uzey

-0.14

isser

-0.14

eko

-0.14

eor

-0.14

eyh

-0.14

 gere

-0.14

POSITIVE LOGITS

 assembled

0.30

 gathered

0.24

 audiences

0.24

sembled

0.22

 audience

0.22

 listeners

0.21

 assembly

0.20

 assemblies

0.18

 gathering

0.18

 assemble

0.18

Activations Density 0.137%

occurrences of speeches or addresses made to groups or assemblies

No Comments

No Known Activations

occurrences of speeches or addresses made to groups or assemblies

No Comments

No Known Activations