INDEX

Explanations

references to family relationships and dynamics

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 itself

-0.22

abar

-0.14

BOSE

-0.13

mÃ©na

-0.13

pNet

-0.13

adle

-0.13

vat

-0.13

ww

-0.13

eniable

-0.13

elden

-0.13

POSITIVE LOGITS

-in

0.23

 whom

0.20

's

0.20

(s

0.19

’s

0.19

/my

0.16

-IN

0.15

/company

0.15

folk

0.15

-than

0.15

Activations Density 0.208%

references to family relationships and dynamics

No Comments

No Known Activations