INDEX

Explanations

terms and references related to veterans and their experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

omo

-0.16

vier

-0.15

ances

-0.15

 pÃ¡s

-0.15

vat

-0.15

 Rodgers

-0.14

rikes

-0.14

ĳľ

-0.14

REDENTIAL

-0.14

omen

-0.14

POSITIVE LOGITS

coe

0.15

é¡¹

0.15

ship

0.15

Toolkit

0.14

Ú©Ø²

0.14

/current

0.14

edb

0.14

iced

0.14

.jupiter

0.14

vern

0.14

Activations Density 0.011%

terms and references related to veterans and their experiences

No Comments

No Known Activations