INDEX

Explanations

phrases related to comparison and evaluating differences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

anna

-0.17

ynet

-0.16

ereotype

-0.16

çĦ¶

-0.15

elry

-0.15

Ã¨n

-0.15

tingham

-0.14

elt

-0.14

zh

-0.14

ough

-0.14

POSITIVE LOGITS

 apples

0.24

isons

0.21

 unfavor

0.20

Against

0.19

 favor

0.19

 against

0.19

 favour

0.19

èĤ©

0.17

favor

0.17

ISON

0.17

Activations Density 0.032%

phrases related to comparison and evaluating differences

No Comments

No Known Activations