INDEX

Explanations

terms related to fortifications and historical structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

heet

-0.15

ouver

-0.15

.AutoComplete

-0.14

 Alley

-0.14

 buttonText

-0.14

 Laden

-0.14

iator

-0.14

Ø§ÙĦØ¨

-0.14

spot

-0.14

hin

-0.14

POSITIVE LOGITS

 complex

0.15

 Sites

0.15

eview

0.14

icensing

0.14

laughs

0.14

ebi

0.14

 Personnel

0.13

{?

0.13

roach

0.13

ãĥ

0.13

Activations Density 0.055%

terms related to fortifications and historical structures

No Comments

No Known Activations