INDEX

Explanations

proper nouns and names, particularly related to familial relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

.functional

-0.17

ague

-0.16

-0.15

LabelText

-0.15

Î½Ïİ

-0.15

jac

-0.15

andbox

-0.14

baseUrl

-0.14

subtype

-0.14

aved

-0.14

POSITIVE LOGITS

0.31

esan

0.19

 Ð±

0.17

hti

0.17

)b

0.16

Âłb

0.16

 Twin

0.15

RuleContext

0.15

ÐºÐ¼

0.14

å«

0.14

Activations Density 0.008%

proper nouns and names, particularly related to familial relationships

No Comments

No Known Activations